Image Recognition in Python with TensorFlow and Keras
Introduction
One of the most common utilizations of TensorFlow and Keras is the recognition/classification of images. If you want to learn how to use Keras to classify or recognize images, this article will teach you how.
Definitions
If you aren’t clear on the basic concepts behind image recognition, it will be difficult to completely understand the rest of this article. So before we proceed any further, let’s take a moment to define some terms.
TensorFlow/Keras
Credit: commons.wikimedia.org
TensorFlow is an open source library created for Python by the Google Brain team. TensorFlow compiles many different algorithms and models together, enabling the user to implement deep neural networks for use in tasks like image recognition/classification and natural language processing. TensorFlow is a powerful framework that functions by implementing a series of processing nodes, each node representing a mathematical operation, with the entire series of nodes being called a “graph”.
In terms of Keras, it is a high-level API (application programming interface) that can use TensorFlow’s functions underneath (as well as other ML libraries like Theano). Keras was designed with user-friendliness and modularity