Over the last couple of years, image recognition software has become increasingly in demand. It is not a coincidence that this demand has coincided with the advancements of big data storage. Google Photos, Facebook, and Apple all utilize image classification software to tag photos for their users. Much of the image recognition software used by these companies are powered by deep learning models built on top of popular libraries such as TensorFlow. This chapter extends the technique of deep learning by leveraging the training of one set of images to the learning or recognition of another set of images. This concept is referred to as transfer learning. In this chapter, we will focus on leveraging transfer learning to recognize the top two football players in the world:
- Lionel Messi
- Cristiano Ronaldo
Take a look at this photo: