如何在Keras的LSTM中修复以下错误？如果RNN是有状态的，请指定`batch_input_shape`

如何解决如何在Keras的LSTM中修复以下错误？如果RNN是有状态的，请指定`batch_input_shape`

在Keras中运行LSTM时出现以下错误：

ValueError: If a RNN is stateful,it needs to kNow its batch size. Specify the batch size of your input tensors: 
- If using a Sequential model,specify the batch size by passing a `batch_input_shape` argument to your first layer.
- If using the functional API,specify the batch size by passing a `batch_shape` argument to your Input layer.

我有一个Pandas数据框，它是按分钟索引的时间序列，训练集和测试集为X_train,X_test,y_train,y_test = train_test_split(X,y,test_size = .2,shuffle = False)。 X_train.shape是（27932，7），而X_test.shape是（6984，7）。我将X_train和X_test标准化并重塑为3D形式：

# normalizing the data
ss = StandardScaler()
X_train = ss.fit_transform(X_train)
X_test = ss.transform(X_test)

X_train = X_train.reshape(6983,4,X_train.shape[1])
X_test = X_test.reshape(1746,X_test.shape[1])
y_train = y_train.values.reshape(6983,1)
y_test = y_test.values.reshape(1746,1)

X重塑背后的逻辑是，我希望我的LSTM在6983个样本上学习4个时间步长（即4分钟）的样本。我想针对(X_train.shape[0],1,X_train.shape[1])的重塑进行测试。

我的LSTM如下：

# Creating our model's structure
model = Sequential()
model.add(Bidirectional(LSTM(4,batch_input_shape = (X_train.shape[0],X_train.shape[1],X_train.shape[2]),return_sequences = True,stateful = True)))
model.add(Dropout(0.2))
model.add(Bidirectional(LSTM(4)))
model.add(Dense(1,activation = 'sigmoid'))
es = EarlyStopping(monitor = 'val_loss',patience = 10)

# Compiling the model
model.compile(loss = 'binary_crossentropy',optimizer = 'adam',metrics = ['Recall'])

# Fitting the model
history = model.fit(X_train,epochs = 50,verbose = 1,validation_data = (X_test,y_test),callbacks = [es])

具有讽刺意味的是，即使我在LSTM的第一层中明确声明了batch_input_shape和stateful = True，我仍然遇到上述错误。如果LSTM使用X_train的3D形状(X_train.shape[0],X_train.shape[1])和X_test的3D形状(X_test.shape[0],X_test.shape[1])，我运行LSTM没问题。

我的代码的哪一部分触发了错误？

顺便说一句，我无法通过比代码中描述的更多的隐藏单元来提高LSTM的性能。这看起来令人惊讶吗？