トップ新着トレンドコメント過去質問紹介求人

butanyways

no profile record

投稿

Build a Deep Learning Library

zekcrates.quarto.pub

134 ポイント·投稿者 butanyways·6 か月前·15 コメント

コメント

·5 か月前·議論

Good introduction! Building pytorch-lite using python and numpy is the way to go.

Free book: https://zekcrates.quarto.pub/deep-learning-library/

Ml by hand : https://github.com/workofart/ml-by-hand

Micrograd: https://github.com/karpathy/micrograd

·6 か月前·議論

maybe creating a simple "pytorch like library" and training models using that? No?

·6 か月前·議論

maybe we can create one ourselves. Posted this a few days ago here. A decent read: https://zekcrates.quarto.pub/deep-learning-library/

·6 か月前·議論

Yes i've read your blogposts way back then. Nice work with the gpt-2!!

·6 か月前·議論

thanks!!

·6 か月前·議論

If you are asking about the "micrograd" video then yes a little bit. "micrograd" is for scalars and we use tensors in the book. If you are reading the book I would recommend to first complete the series or atleast the "micrograd" video.

·6 か月前·議論

Yes!!

·6 か月前·議論

Its nice! Yeah a lot of the heavy lifting is done by Numpy.

·6 か月前·議論

I agree! What NumPy is doing is actually quite beautiful. I was thinking of writing a custom c++ backend for this thing. Lets see what happens this year.