Tools / Data science and machine learning libraries
PyTorch
The library most deep learning is written in. Tensors, automatic gradients, training loops and ready-made models.
About 30 hours of study. It builds on Machine learning.
Where to learn it
Daniel Bourke
The whole video, alongside the book
The same author and the same notebooks as the book.
About 25 hours. Covers the first chapters of the book.
Daniel Bourke
The exercises at the end of chapters 00–06
Section not checked yet
Wrong chapter, dead link, or know something better? Tell us on GitHub.
Your route to PyTorch
Pick where you’re starting from. Anything your background already covers is left out, and the rest is put in order.
5 stops to go, about 210 hours of study.
Open a stop to see the book, the video course and the practice for it. Tick its circle when you've finished.
- 40 h
Maths foundations. Ready to start.
- 40 h
Maths foundations. Ready to start.
- 40 h
Programming. Ready to start.
- 60 h
Machine learning. After Linear algebra, Probability and Programming in Python.
- Tool30 h
Machine learning. After Machine learning.
That's the whole route to PyTorch.
Which roles ask for it
- Machine learning engineer in the first year
- Deep learning engineer (vision / language) to get hired
What it needs and what it leads to: PyTorch on the map.