In this chapter, we will look at two of the most common modules of the TensorFlow API: tf.data and tf.estimator.
The TensorFlow 1.x design was so good that almost nothing changed in TensorFlow 2.0; in fact, tf.data and tf.estimator were the first two high-level modules introduced during the life cycle of TensorFlow 1.x.
The tf.data module is a high-level API that allows you to define high-efficiency input pipelines without worrying about threads, queues, synchronization, and distributed filesystems. The API was designed with simplicity in mind to overcome the usability issues of the previous low-level API.
The tf.estimator API was designed to simplify and standardize machine learning programming, allowing to train, evaluate, run inference, and export for serving a parametric model, letting the user focus on the model and input definition...
