Skip to content

Unofficial implementation of DualPatchNorm using tensorflow2. Include ablation study code too.

Notifications You must be signed in to change notification settings

dslisleedh/DualPatchNorm-tensorflow2

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DualPatchNorm-tensorflow2

Unofficial implementation of DualPatchNorm using tensorflow2. Include ablation code too.
Paper: Dual PatchNorm(Google Research and Brain Team)

Note

Not completed codes.

How to run

git clone [email protected]:dslisleedh/DualPatchNorm-tensorflow2.git
cd DualPatchNorm-tensorflow2
conda env create -f environment.yaml
conda activate dpn
python train.py 

If you have never downloaded the imagenet_resized 64x64 using tensorflow_datasets, run donwload_datasets.py before run train.py
Default config is set run HPO that takes lots of time.
Disable HPO if you just want to run code for once.

python train.py hpo=False hparams.$ANY_HPARAMS_IN_CONFIG=...

About

Unofficial implementation of DualPatchNorm using tensorflow2. Include ablation study code too.

Topics

Resources

Stars

Watchers

Forks

Languages