PyTorch Tutorial: A Quick Preview

pi torch is one of the most popular open source deep learning frameworks both researchers and developers use pi torch because it provides fast flexible experimentation and a seamless transition to production deployment pi torch is built to use the power of GPUs for faster training and is deeply integrated into Python making it easy to get started one of the best ways to get started with PI torch is by going through the tutorial deep learning with PI torch a 60-minute blitz authored by so meet chintala upon completion of this tutorial you'll understand what PI torch and neural

networks are and be able to build and train a small neural network that can classify images keep in mind that this tutorial assumes that you have a basic familiarity with numpy a Python library for scientific computing all of the modules in the 60-minute blitz have links to google collab so you can immediately run code and get hands-on experience with pi torch you can also download the notebooks and run them locally now let's take a look at the topics we'll cover in the Blitz the tutorial is broken out into four different modules in the first module

what is pi torch you'll learn the fundamental technical details of pi torch such as tensors and multiple syntaxes of operations in the second module you'll learn about automatic differentiation through a PI torch package called Auto grad in the third module you'll follow a typical procedure for training and neural network by defining the neural network computing the loss and propagating gradients back into the network's parameters finally you'll get to put what you learned in the first three modules into a real-life example training an image classifier to automatically label images let's get started [Music] you