butanyways

5 months agodiscuss

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

butanyways

6 months agodiscuss

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

butanyways

6 months agodiscuss

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

butanyways

6 months agodiscuss

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

butanyways

6 months agodiscuss

thanks!!

butanyways

6 months agodiscuss

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.

butanyways

6 months agodiscuss

Yes!!

butanyways

6 months agodiscuss

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

butanyways

6 months agodiscuss

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.

butanyways

Submissions

Build a Deep Learning Library

comments