Summary

In this chapter, we worked on classifying clothing images using CNNs. We started with a detailed explanation of the individual components of a CNN model and learned how CNNs are inspired by the way our visual cells work. We then developed a CNN model to categorize fashion-MNIST clothing images from Zalando. We also talked about data augmentation and several popular image augmentation methods. We practiced transfer learning with ResNets, after discussing the evolution of CNN architectures and pretrained models.

In the next chapter, we will focus on another type of deep learning network: Recurrent Neural Networks (RNNs). CNNs and RNNs are the two most powerful deep neural networks that make deep learning so popular nowadays.