keras LSTM多任务学习功能api输入数据

Question

我有两个数据框用于多任务学习，我想预测两个不同数据集的2值

我得到这个错误

ValueError: Data cardinality is ambiguous:
  x sizes: 24, 41
  y sizes: 24, 41
Please provide data which shares the same first dimension.

# input tensor
X_data = trainxx.reshape((trainxx.shape[0], 1, trainxx.shape[1]))
(24, 1, 10)
B_data = trainxx9.reshape((trainxx9.shape[0], 1, trainxx9.shape[1]))
(42, 1, 15)
y values are numpy array
ytrainxx
(24,)
ytrainxx9
(42,)
 

i1 = Input((24,10)) 
i2 = Input((42,15))

l1 = LSTM(24)(i1)
flat_layer = Flatten()(l1)
l2 = LSTM(42)(i2)
flat_layer2 = Flatten()(l2)


output1 = Dense(1, activation='sigmoid')(flat_layer)
output2 = Dense(1, activation='sigmoid')(flat_layer2)

model = tf.keras.Model(inputs=[i1,i2], outputs=[output1,output2])
model.compile('sgd', 'mse')
model.fit(x=[X_data,B_data], y=[ytrainxx,ytrainxx9])