In this video, we cover the third lab for the course, on the ResNet+Transformer architecture of the text recognition model and the handwritten paragraph dataset we use to train that model.
Follow along on Colab here:
https://fsdl.me/lab03-colab
To run the labs on your own machine, check out the GitHub repo here:
https://fsdl.me/2022-repo-labs
and follow the setup instructions here:
http://fsdl.me/2022-local-setup
Outline:
00:00 Getting started with Lab 03
01:43 The Resnet Transformer and the Transformer LitModel
04:31 Training the Resnet Transformer to read paragraphs of text
09:17 Exercises
Subscribe to our channel or sign up at https://fullstackdeeplearning.com/cou... to follow along with the 2022 course!