TensorFlow is a popular open source library that's used for implementing machine learning and deep learning. It was initially built at Google for internal consumption and was released publicly on November 9, 2015. Since then, TensorFlow has been extensively used to develop machine learning and deep learning models in several business domains.
To use TensorFlow in our projects, we need to learn how to program using the TensorFlow API. TensorFlow has multiple APIs that can be used to interact with the library. The TensorFlow APIs are divided into two levels:
- Low-level API: The API known as TensorFlow core provides fine-grained lower level functionality. Because of this, this low-level API offers complete control while being used on models. We will cover TensorFlow core in this chapter.
- High-level API: These APIs provide high-level functionalities that have been built on TensorFlow core and are comparatively easier to learn and implement. Some high-level APIs include Estimators, Keras, TFLearn, TFSlim, and Sonnet. We will also cover Keras in this chapter.