To get the most out of this book

This book does not assume any specialist knowledge, only solid general computer skills. Python is a relatively easy (and incredibly useful!) language to learn, so don't worry if you have limited or no programming background. 

The book does contain some relatively simple mathematics, and some theory, that some readers may find difficult at first. Deep learning models are complex systems and understanding the behavior of even simple neural networks is a non-trivial exercise. Fortunately, PyTorch acts as a high-level framework around these complicated systems, so it is possible to achieve very good results without an expert understanding of the theoretical foundations. 

Installing the software is easy, and essentially only two packages are required: the Anaconda distribution of Python, and PyTorch itself. The software runs on Windows 7 and 10 , macOS 10.10 or above, and most versions of Linux. It can be run on a desktop machine or in a server environment. All the code in this book was tested using PyTorch version 1.0 and Python 3, running on Ubuntu 16.