PyTorch is an open source machine learning framework and as stated in their website, it accelerates the path from research prototype to production.
Welcome to the “Zero to Comfortable tutorial” on PyTorch.
No matter whether you are a machine learning enthusiast or an active practitioner, this tutorial is for you and designed specifically to help you understand how PyTorch works and what are the ideal conditions for considering PyTorch as a Machine Learning / Neural Network framework for your work.
This tutorial will also help you understand one of the most prominent feature of PyTorch called autograd or automatic differentiation using multiple examples and exercises. Last but not the least we’ll also see how PyTorch tensors can work seamlessly with tensors created using NumPy.
This tutorial will not make you an expert in PyTorch but shall cover enough things to make you comfortable with it so that you can test your next big ideas / solutions in PyTorch or may even adopt it for the same. You’ll not only do some classroom exercises but will also be provided with the homework exercises to understand it better. Don’t worry, I’ll share all the exercises and solutions post tutorial session on GitHub