FastAI to PyTorch conversion

Sorry I’m posting this here I’m not sure which section to post in. I have been taking the FastAI course. And if anyone else has taken this course they know that they use their own python library called fastai that is a wrapper for PyTorch functions. This is effective for having time to explain theory, but I am wondering how these same methods would be implemented directly from PyTorch. Has anyone seen any blog posts or anything where someone has rewritten some fastai lessons in base PyTorch commands? I found one here: but that is all I could find - it converts lesson 6 in FastAI Part I. Thanks!

Here’s the GitHub: