To get the most out of this book
To get the most out of this book, you should be comfortable with coding in Python (in Jupyter notebooks and in standalone Python modules) and with the core concepts of machine learning. This book explains a broad variety of deep learning applications but doesn't go into the internals of deep learning itself. If you have a basic grasp of how deep learning works, you will find the more advanced examples in the book easier to follow.
Most of the code examples in this book are designed to be run in GPU-enabled cloud deep learning Jupyter notebook environments. You have the choice of using either Paperspace Gradient or Google Colab for these examples, with Gradient being the recommended environment. The model deployment examples in Chapter 7, Deployment and Model Maintenance, and Chapter 8, Extended fastai and Deployment Features, are designed to be run on your local system and require fastai and PyTorch to be installed on your local system.
If you are using the digital version of this book, we advise you to type the code yourself or access the code via the GitHub repository (link available in the next section). Doing so will help you avoid any potential errors related to the copying and pasting of code.
