Chapter 2: Performing Image Classification
Computer vision is a vast field that takes inspiration from many places. Of course, this means that its applications are wide and varied. However, the biggest breakthroughs over the past decade, especially in the context of deep learning applied to visual tasks, have occurred in a particular domain known as image classification.
As the name suggests, image classification consists of the process of discerning what's in an image based on its visual content. Is there a dog or a cat in this image? What number is in this picture? Is the person in this photo smiling or not?
Because image classification is such an important and pervasive task in deep learning applied to computer vision, the recipes in this chapter will focus on the ins and outs of classifying images using TensorFlow 2.x.
We'll cover the following recipes:
- Creating a binary classifier to detect smiles
- Creating a multi-class classifier to play Rock Paper Scissors
- Creating a multi-label classifier to label watches
- Implementing ResNet from scratch
- Classifying images with a pre-trained network using the Keras API
- Classifying images with a pre-trained network using TensorFlow Hub
- Using data augmentation to improve performance with the Keras API
- Using data augmentation to improve performance with the tf.data and tf.image APIs
