Chapter 7. Practical Tools, Tips, and Tricks

This chapter contains material that we, your authors, have encountered during our professional work as well as while working on this book, primarily during experimentation. The material covered here doesn’t necessarily fit in any single chapter; rather, it’s material that deep learning practitioners could find useful on a day-to-day basis across a variety of tasks. In line with the “practical” theme, these questions cover a range of helpful pragmatic guidelines across topics including setting up an environment, training, model interoperability, data collection and labeling, code quality, managing experiments, team collaboration practices, privacy, and further exploration topics.

Due to the fast-changing pace of the AI field, this chapter is a small subset of the “living” document hosted on the book’s Github repository (see at code/chapter-9, where it is constantly evolving. If you have more questions or, even better, answers that might help other readers, feel free to tweet them @PracticalDLBook or submit a pull request.


Q: I came across an interesting and useful Jupyter Notebook on GitHub. Making the code run will require cloning the repository, installing packages, setting up the environment, and more steps. Is there an instant way to run it interactively?

Simply enter the Git repository URL into Binder (, which will turn it into a collection of interactive notebooks. Under ...

Get Practical Deep Learning for Cloud, Mobile, and Edge now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.