我在试一个MCQ的干扰发生器，有人能解释以下错误吗？

Question

以下是出现错误的代码：

model = Sequential()
model.add(LSTM(256, input_shape=(X.shape[0], X.shape[1])))
model.add(Dropout(0.2))
model.add(Dense(y1.shape[0], activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam')

拟合数据：

model.fit(X, y1, epochs=20, batch_size=128)
model.fit(X, y2, epochs=20, batch_size=128)
model.fit(X, y3, epochs=20, batch_size=128)

以下是输出代码：

Traceback (most recent call last):
File "1.py", line 139, in <module>
    model.fit(X, y1, epochs=20, batch_size=128)

File "C:\Users\Rohit\AppData\Local\Programs\Python\Python37\lib\site-packages\keras\engine\training.py", line 1154, in fit
    batch_size=batch_size)

File "C:\Users\Rohit\AppData\Local\Programs\Python\Python37\lib\site-packages\keras\engine\training.py", line 579, in _standardize_user_data
    exception_prefix='input')

File "C:\Users\Rohit\AppData\Local\Programs\Python\Python37\lib\site-packages\keras\engine\training_utils.py", line 135, in standardize_input_data
    'with shape ' + str(data_shape))

ValueError: Error when checking input: expected lstm_1_input to have 3 dimensions, but got array with shape (13595, 2)