Skip to content
/ wide_resnet_wfixup_jax Public

An implementation of WideResNets with Fixup initialization in Jax/Flax. This can be useful for use cases where Batch Normalization should be avoided (for example when using the Laplace approximation to the Bayesian posterior).

0 stars 0 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

konstantinos-p/wide_resnet_wfixup_jax

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
.idea
.idea
 
 
conf
conf
 
 
.gitignore
.gitignore
 
 
README.md
README.md
 
 
fixup_initializer.py
fixup_initializer.py
 
 
models.py
models.py
 
 
test_models.py
test_models.py
 
 
train.py
train.py
 
 

Repository files navigation

WideResNets with Fixup initialization in jax/flax.

An implementation of WideResNets with Fixup initialization in Jax/Flax. This can be useful for use cases where Batch Normalization should be avoided (for example when using the Laplace approximation to the Bayesian posterior).

✉️ Contact Information

You can contact me at any of my social network profiles:

Or via email at cwstas2007@hotmail.com

About

An implementation of WideResNets with Fixup initialization in Jax/Flax. This can be useful for use cases where Batch Normalization should be avoided (for example when using the Laplace approximation to the Bayesian posterior).

Topics

flax fixup wideresnet jax bayesianneuralnetwork

Resources

Readme
Activity

Stars

0 stars

Watchers

2 watching

Forks

0 forks
Report repository

Releases

No releases published

Packages

No packages published

Languages