Hi everyone. I am currently overwhelmed by the number of resources available. Is it still advisable to go through the fastai book given that there are newly uploaded resources for part 2 of the course?
Is it best to just focus on the latest part 1 and 2 uploaded or the book is still relevant? Or should I do part 1 of the book and then do part 2 (latest version) that is now widely available? Do you have any recommended approach? Thank you.
I think the recommendation is to to do part 1 before doing part 2. Or if you didn’t do part 1 but are pretty familiar with PyTorch and deep learning applications, you can jump right into part 2.
In my experience the book is still highly relevant,vand covers parts of part 1 and actually much more (also stuff that was covered in part 1 and part 2 of previous fastai courses).
If you are still fairly new to deep learning, i would recommend starting with part 1, and perhaps read most of the book, then continue with part 2.
Based on your answer, do you recommend that I just focus on part 1 of the book which is from chapters 1 to 11 I think. And then just jump straight to latest version of part 2? Thank you.
I’d say it really depends on your goals. If you “just” want to get as quickly as possible to stable diffusion, you could perhaps even skip parts of the stuff around tabular, collaborative filtering and text. However if your goals is to become an all round expert at deep learning, you probably want to spend a decent amount of time also on those applications, and take your time to study things thoroughly.
The latter would be my personal recommendation, but it all depends on where you are in life, how much time you have and what your goals are:)
Hope this helps!
Book is great, but I would start with the videos for part 1, even you’re familiar with deep learning. Then try to run every cell and understand the code. It is nice to check the book too.It is still relevant but it is not follow the course chronologicallly.
Goodnluck.