Skip to content

utkarshgill/mnist_from_scratch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 

Repository files navigation

Train MNIST using numpy with manual backprop (somehow more accurate than pytorch)

pytorch loss.backward() : 0.964

backprop by hand : 0.977

image

About

training MNIST with numpy (accuracy > pytorch)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors