Chapter 6. TensorFlow and Keras for Predictive Analytics
TensorFlow was created and made open source by Google. It is one of the most-used platforms worldwide for machine learning. Tensorflow.org defines TensorFlow as “an end-to-end platform for machine learning.”
TensorFlow has wide-ranging applications, including structured data processing, automated image classification, advanced optical character recognition (OCR), video analysis, and sentiment analysis, to name a few. It provides the tools for data ingestion and processing, ML model creation, ML model training, ML model deployment, and ML model life cycle management. Support for graphics processing units (GPUs) and tensor processing units (TPUs) allows users to work on compute-intensive deep neural networks. The fact that models can be deployed on a wide range of devices, including mobile phones, client machines and servers, edge devices, and the cloud, is one of the many reasons for its high rate of adoption among data professionals and enterprises. Figure 6-1 provides a high-level picture of the TensorFlow platform. You can find excellent documentation on the TensorFlow site.
Figure 6-1. TensorFlow platform
Keras is a deep learning API built on top of TensorFlow 2. Keras simplifies the adoption of deep learning for individuals and enterprises by providing an easy-to-use API with extensive documentation. Since it is built ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access