← All projects
Learning resources

Deep Learning (PyTorch) - ND101 v7

Hands-on lessons and projects that teach how to build deep learning models with PyTorch.

What it does

This is a collection of tutorial notebooks from Udacity's Deep Learning Nanodegree course. Notebooks are interactive documents that mix explanations with code you can run step by step. They use PyTorch, a popular toolkit for building AI models.

The lessons walk you through building different kinds of neural networks (computer programs loosely inspired by the brain that learn from examples). Topics include recognizing handwritten digits and images, judging whether a movie review is positive or negative, generating new images, and turning summer photos into winter ones.

It also includes the starting code for the course projects, such as predicting bike rentals, classifying dog breeds from photos, generating TV scripts, and creating new face images. There is extra material on TensorFlow and Keras, two other AI toolkits.

Who it's for

Learners who know some Python and want to understand how deep learning works by building models themselves.

Can I use it without coding?

Developers only. The lessons involve writing and running Python code in notebooks after setting up a programming environment from the command line. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Mac, Windows, Linux
Privacy
Runs on your own device: your data stays with you
API key
Not needed

Try it

  1. Install Miniconda for your computer from the link in the README.
  2. Download the course materials and set up a new environment with PyTorch, following the README's steps.
  3. Open the notebooks with Jupyter and start with the introduction lessons.

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • Plain-AyI is an independent guide and doesn't host or review the software it lists. Please check each project's official page before installing.
  • License (MIT): Very permissive: free to use, change and share, including for business.
  • More on staying safe