October 2020
Beginner to intermediate
468 pages
9h 39m
English
The applications of artificial intelligence in computer vision include robotics, self-driving cars, facial recognition, recognizing diseases in biomedical images, and quality control in manufacturing, among many others.
In this chapter, we'll start with image recognition (or image classification), where we'll look into basic models and more advanced models. We'll then create images using Generative Adversarial Networks (GANs).
In this chapter, we will cover the following recipes:
We'll use many standard libraries, such as NumPy, Keras, and PyTorch, but we'll also see a few more libraries that we'll mention at the beginning ...