22.02.2024 Views

Daniel Voigt Godoy - Deep Learning with PyTorch Step-by-Step A Beginner’s Guide-leanpub

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

After choosing a repository, it will list the available notebooks and corresponding

links to open them in a new browser tab.

Figure S.1 - Google Colab’s special URL

You also get access to a GPU, which is very useful to train deep learning models

faster. More important, 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 to 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." [19]

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, but let’s leave it at that), clone the repository, and start Jupyter. This

allows you to have access to Jupyter’s home page in your browser, just like 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 (https://mybinder.org/) and type in the URL to the GitHub

repository you want to explore (for instance,

https://github.com/dvgodoy/PyTorchStepByStep) 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 this book’s repository directly using the following

Environment | 9

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!