tf2.0训练网络，使用官方预训练模型和权重时，在保存模型和参数时，出现这个错误：
代码：

model.save('model36_5.h5')
model.save_weights('weight_tf_model36_5.h5')

报错信息

 NotImplementedError: Saving the model to HDF5 format requires the    
   model to be a Functional model or a Sequential model. It does not   
   work  for subclassed models, because such models are defined via 
   the body   of a Python method, which isn't safely serializable. Consider 
   saving to    the Tensorflow Saved Model format (by setting   
   save_format="tf") or    using `save_weights`.

错误原因：
自定义模型只保存参数（model_weight模型），官方模型保存参数和权重（.h5模型）
修改为：

model.save_weights('weight_tf_model36_5.h5')

完成！
参考文章：解决tf2 NotImplementedError: Saving the model to HDF5 format requires the model to be a Functional mod