Production: TensorFlow and Keras

Question

I always here about TensorFlow is good because it is used for deploying and production. Does that mean that people don't use Keras for deploying models? If keras is now integrated into TensorFlow, does that mean that it can also be used for deployment and production?

Answer 1

Once model has been trained with Keras

1. It can be exported to TensorFlow model OR
2. With tf.keras it can be served as http service

Examples :

https://towardsdatascience.com/deploying-keras-models-using-tensorflow-serving-and-flask-508ba00f1037

https://medium.com/tensorflow/training-and-serving-ml-models-with-tf-keras-fd975cc0fa27

https://medium.com/@mr.acle/exporting-deep-learning-models-from-keras-to-tensorflow-serving-7d4a6e49ce3