The previous chapter introduced the basics of how machine learning works. You saw how to get started with programming using neural networks to match data to labels, and from there how to infer the rules that can be used to distinguish items. A logical next step is to apply these concepts to computer vision, where we will have a model learn how to recognize content in pictures so it can “see” what’s in them. In this chapter you’ll work with a popular dataset of clothing items and build a model that can differentiate between them, thus “seeing” the difference between different types of clothing.
Recognizing Clothing Items
For our first example, let’s consider what it takes to recognize items of clothing in an image. Consider, for example, the items in Figure 2-1.
Figure 2-1. Examples of clothing
There are a number of different clothing items here, and you can recognize them. You understand what is a shirt, or a coat, or a dress. But how would you explain this to somebody who has never seen clothing? How about a shoe? There are two shoes in this image, but how would you describe that to somebody? This is another area where the rules-based programming we spoke about in Chapter 1 can fall down. Sometimes it’s just infeasible to describe something with rules.
Of course, computer vision is no exception. But consider how you learned to recognize ...
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.
