Output tensors of a Functional model must be the output of a TensorFlow `Layer` (thus holding past

继续遇到错误，改正错误，错误如题。

参考链接：python - ValueError: Output tensors of a Functional model must be the output of a TensorFlow `Layer` (thus holding past layer metadata) - Stack Overflow

大概什么意思呢，就是说你应该先定义好函数，再把参数什么的传过来。

照着这里的代码定义个函数,后续在主函数中再继续调用等等。

def ComputeSumModel(tensor):
    inputs = Input(shape = tf.shape(tensor))
    outputs = ComputeSum(len(tensor))(tensor)
    
    model = keras.Model(inputs = inputs, outputs = outputs)

    return model

model=MultiModel(input_shape=(9, 1))   #输入是你自己的输入
model.compile(loss='categorical_crossentropy', optimizer=Adam(), metrics=['accuracy'])
model.fit(X_train, Y_train, batch_size=100, epochs=5, verbose=1, validation_data=(x_test, y_test))