解决tf2 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 SavedModel format (by setting save_format=“tf”) or using save_weights.
代码
model.save('save_model.h5')
new_model = keras.models.load_model('save_model.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 SavedModel format (by setting save_format="tf") or using `save_weights`.
解决办法
model.save_weights('model_weight')
new_model = MyNet()
new_model.load_weights('model_weight')
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）
欢迎大家交流学习，任何问题都可以留言
版权声明：本文为weixin_41194171原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接和本声明。