Why PyTorch?

Learn why PyTorch is the best choice for developing Deep Learning models.

We'll cover the following

Why use PyTorch?

First, coding in PyTorch is fun! Really, there is something about it that makes it very enjoyable to write code. Some say it is because it is very pythonic or maybe there is something else. Who knows? By the end of this course, I hope you feel that way too!

Second, maybe there are some unexpected benefits for your health. Check Andrej Karpathy’s tweet about it!

But jokes aside, PyTorch is the fastest-growing framework for developing Deep Learning models, and it has a huge ecosystem. That is, there are many tools and libraries developed on top of PyTorch. It is the preferred framework in academia already, and it is making its way into the industry.

Several companies are already powered by PyTorch. To name a few:

  • Facebook: The company is the original developer of PyTorch, released in October 2016.

  • Tesla: Watch Andrej Karpathy (AI Director at Tesla) discuss “how Tesla is using PyTorch to develop full self-driving capabilities for its vehicles” in this video.

  • OpenAI: In January 2020, OpenAI decided to standardize its Deep Learning framework on PyTorch (source).

  • Fast.ai: Fast.ai is a library built on top of PyTorch to simplify model training, and it is used in its Practical Deep Learning for Coders course. The fast.ai library is deeply connected to PyTorch, and “you can’t become really proficient at using fastai if you don’t know PyTorch well, too”. (source)

  • Uber: The company is a significant contributor to PyTorch’s ecosystem having developed libraries like Pyro (probabilistic programming) and Horovod (a distributed training framework).

  • Airbnb: PyTorch sits at the core of the company’s dialog assistant for customer service (source).

This course aims to get you started with your own PyTorch projects while giving you a solid understanding of how it works.