After releasing the beta version of TensorFlow 2.0 in June, Google announced its final release on Monday. This release comes with tighter integration with Keras, eager execution enabled by default, promises three times faster training performance, a cleaned-up API, and more. One of the important updates in TensorFlow 2.0 is its tighter integration with Keras, a popular high-level API used for easy and fast prototyping, building, and training deep learning models. This will enable developers to easily leverage its various model-building APIs including Sequential, Functional, and Subclassing. Explaining the motivation behind this change, the TensorFlow team wrote, "By establishing Keras as the high-level API for TensorFlow, we are making it easier for developers new to machine learning to get started with TensorFlow. A single high-level API reduces confusion and enables us to focus on providing advanced capabilities for researchers."