8000 GitHub - runjerry/gtk-sgd: sgd with generalized tangent kernel
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

runjerry/gtk-sgd

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

88 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Train CIFAR10 with PyTorch

This is a demo implementation of affine transformed sgd under randomly chozen generalized tangent kernel (GTK). It can be applied to any sgd-bsed optimizers, I simply use the current forked repo as an example.

Prerequisites

  • Python 3.6+
  • PyTorch 1.0+

Training

# Start training with: 
python main.py --model mlp1 --act gelu --lr 0.1 --optimizer gtk --seed 0

About

sgd with generalized tangent kernel

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%
0