A merge layer should be called on a list of inputs

[1073521013]

Describe the bug(问题描述) 保存模型model.save，然后加载的时候，tf.keras.models.load_model报错"A merge layer should be called on a list of inputs",官方找到类似问题说更新keras,现在最新2.4.3还是报错

To Reproduce(复现步骤) DeepFM模型完整保存，model.save()

Operating environment(运行环境):

• python version 3.7
• tensorflow version 2.2.0
• keras version 2.4.3

Additional context Add any other context about the problem here.

[shenweichen]

请提供一份最短可复现的代码，方便我们排查问题

[Darinyazanr]

## examples/run_classification_criteo.py

model = DeepFM(linear_feature_columns, dnn_feature_columns, task='binary')
model.compile("adam", "binary_crossentropy",
              metrics=['binary_crossentropy'], )

history = model.fit(train_model_input, train[target].values,
                    batch_size=256, epochs=10, verbose=2, validation_split=0.2, )
pred_ans = model.predict(test_model_input, batch_size=256)

print("test_model_input:", test[target].values)
print("pred_ans:", pred_ans)

model.save('./Criteo.pb')
print('#'*120)
import keras
model1=keras.models.load_model('./Criteo.pb')

报上述的那个错误，请问怎么解决呢，辛苦看下？

Operating environment(运行环境):

python version 3.8 tensorflow version 2.3.1 keras version 2.4.3

[feng-intel]

这个问题解决了么？我也遇到了~