July 05, 2020

David's Tips on How to Read Pytorch

Pytorch has a great design: easy and powerful. Easy enough that it is definitely possible to use pytorch without understanding what it is doing or why. But it also gets better the more you understand.

As part of summer school at MIT, next week I'm doing a lecture to introduce students to pytorch. I have written a few code examples that I hope will give students a head start on understanding the design of pytorch. Each concept is illustrated visually with a cute minimal hackable example. All the examples are notebooks that are hosted on Google Colab.

It covers tensor indexing conventions, benchmarks gpu versus cpu speeds, explains autograd with simple systems, and plots what optimizers are doing using 2d problems. Then I put the pieces together with a detailed discussion of network modules and data loaders, training toy networks where the whole space can be visualized as well as a simple but realistic five-minute ResNet training example.

Here are David's Tips on How to Read Pytorch.

Posted by David at July 5, 2020 02:58 PM
Comments

Blog exceptionnel ! Bonne continuité :)

Posted by: chirurgie esthetique at August 10, 2020 08:58 AM

Great work David, despite your busy research schedule. The 'rewriting' paper was truly exceptional and novel.

Posted by: Prameth Gaddale at August 13, 2020 08:41 AM

Thank you for information and tips. Greeting from Indonesia.

Posted by: Lingga at August 26, 2020 03:15 AM
Post a comment









Remember personal info?