在keras中串联多个输入函数API CNN模型

Question

我有8个CNN模型model1，model2，model3，model4，model5，model6，model7，model8，每个模型都具有conv2d，激活，maxpooling和dropout层。我想将它们的输出连接起来，进行编译和拟合，如下图所示：

我在连接，合并和拟合上感到困惑。我的python代码如下：

out1 = Flatten()(model1)
out2 = Flatten()(model2)
out3 = Flatten()(model3)
out4 = Flatten()(model4)
out5 = Flatten()(model5)
out6 = Flatten()(model6)
out7 = Flatten()(model7)
out8 = Flatten()(model8)
merge = Concatenate([out1, out2, out3, out4, out5, out6, out7, out8])

final_out = Dense(classes, activation='softmax')(merge) 

final_model = Model([out1, out2, out3, out4, out5, out6, out7, out8], final_out)

final_model.compile(loss="categorical_crossentr", optimizer= opt, metrics=["accuracy"])

final_model.fit_generator(aug.flow(trainX, trainY, batch_size=BS),validation_data=(testX, testY),
                    steps_per_epoch=len(trainX) // BS, epochs=EPOCHS, verbose=1)

运行程序时，出现以下错误：

Layer dense_1 was called with an input that isn't a symbolic tensor

出什么问题了？如何连接，编译和训练？谁能帮助我，任何信息都将对您有帮助。