Skip to content

Minimal pytorch-like autograd implementation from scratch with Numpy

brrich/pytorch-from-scratch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 

Repository files navigation

Minimal Autograd Neural Net in NumPy

This repo contains a super minimal neural network library and training loop using only NumPy. The file defines a tiny tensor/autograd engine inspired by PyTorch, supporting basic operations and gradient descent. The script includes an example linear regression training run at the bottom. Just for learning fun :)

About

Minimal pytorch-like autograd implementation from scratch with Numpy

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages