5. Style Transfer


This chapter explains the process of using pre-trained models in order to create or make use of well-performing algorithms without having to gather large quantities of data. In this chapter, you will learn how to load a pre-trained model from PyTorch in order to create a style transfer model. By the end of this chapter, you will be able to perform style transfer through the use of pretrained models.


The previous chapter explained the different building blocks of traditional CNNs, as well as some techniques for improving their performance and reducing training time. The architecture explained there, although typical, is not set in stone, and a proliferation of CNN architectures have emerged to solve ...

Get The Deep Learning with PyTorch Workshop now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.