Official repository

This course’s official repository is on GitHub.

It contains one Jupyter notebook for every chapter in this course. Each notebook contains all the code shown in its corresponding chapter, and you should be able to run its cells in sequence to get the same outputs, as shown in the course. I strongly believe that being able to reproduce the results brings confidence to the reader.

Environment

There are three options for you to run the Jupyter notebooks:

Let’s briefly explore the pros and cons of each one of those options:

Google Colab

Google Colab “allows you to write and execute Python in your browser, with zero configuration required, free access to GPUs and easy sharing.”

You can easily load notebooks directly from GitHub using Colab’s special URL. Just type in the GitHub’s user or organization (like the author’s, dvgodoy), and it will show you a list of all its public repositories (like for this course: PyTorchStepByStep).

After choosing a repository, it will also list the available notebooks and corresponding links to open them in a new browser tab.

You also get access to a GPU, which is very useful to train Deep Learning models faster. More importantly, if you make changes to the notebook, Google Colab will keep them. The whole setup is very convenient. The only cons I can think of are:

  • You need to be logged in a Google Account.

  • You need to (re)install Python packages that are not part of Google Colab’s default configuration.

Binder

Binder “allows you to create custom computing environments that can be shared and used by many remote users.”

You can also load notebooks directly from GitHub, but the process is slightly different. Binder will create something like a “virtual machine” (technically, it is a container), clone the repository, and start Jupyter. This allows you to have access to Jupyter’s Home Page in your browser, just like the way you would if you were running it locally, but everything is running in a JupyterHub server on their end.

Just go to Binder’s site, and type in the URL to the GitHub repository you want to explore, and click on Launch. It will take a couple of minutes to build the image and open Jupyter’s home page.

You can also launch Binder for the course’s repository directly using this link.

Get hands-on with 1200+ tech skills courses.