Deep Learning with PyTorch Step-by-Step: Part I - Fundamentals
Learn PyTorch basics: autograd, model classes, datasets, and data loaders. Gain insights into model development while avoiding common pitfalls. Start creating and training your own PyTorch models.
- 92 lessons across 9 modules
- 20 quizzes with instant feedback
- AI Tutor on every lesson
Daniel is a data scientist, teacher, and author of "Deep Learning with PyTorch Step-by-Step: A Beginner's Guide". He has been teaching machine learning and distributed computing technologies at Data Science Retreat, the longest-running Berlin-based bootcamp, since 2016, helping more than 150 students advance their careers. Daniel is also the main contributor of two Python packages: HandySpark and DeepReplay. His professional background includes 20 years of experience working for companies in several industries: banking, government, fintech, retail, and mobility.
Join 3.1 million developers at
What You'll Learn
- Explain why PyTorch is used for deep learning, including its ecosystem and industry adoption
- Implement gradient descent for linear regression in NumPy (forward, MSE loss, gradients, updates)
- Generate reproducible synthetic datasets with noise and perform train-validation splits
- Use PyTorch tensors, devices (CPU/CUDA), and requires_grad to create trainable parameters
- Apply autograd, backward(), and torch.no_grad() to compute gradients and update parameters safely
- Build and train PyTorch models using Modules, optimizers, loss functions, and mini-batch DataLoaders
- Evaluate and deploy binary classifiers using thresholds, confusion matrices, metrics, ROC/PR curves, and logits
Learning Roadmap
1.
Introduction
Introduction
2.
Visualizing Gradient Descent
Visualizing Gradient Descent
3.
A Simple Regression Problem
A Simple Regression Problem
21 Lessons
21 Lessons
4.
Rethinking the Training Loop
Rethinking the Training Loop
17 Lessons
17 Lessons
5.
Going Classy
Going Classy
15 Lessons
15 Lessons
6.
A Simple Classification Problem
A Simple Classification Problem
19 Lessons
19 Lessons
8.
Appendix
Appendix
2 Lessons
2 Lessons
Daniel Voigt Godoy
Daniel is a data scientist, teacher, and author of "Deep Learning with PyTorch Step-by-Step: A Beginner's Guide". He has been teaching machine learning and distributed computing technologies since 2016.
Trusted by 3.1 million developers working at companies
Anthony Walker
@_webarchitect_
Evan Dunbar
ML Engineer
Software Developer
Carlos Matias La Borde
Souvik Kundu
Front-end Developer
Vinay Krishnaiah
Software Developer
Built for 10x Developers
Free Resources
