Skip to content

PyTorch implementation of AAAI2024 paper Agile Multi-Source-Free Domain Adaptation

Notifications You must be signed in to change notification settings

TL-UESTC/Bi-ATEN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Bi-ATEN

Pytorch implementation of Agile Multi-Source-Free Domain Adaptation (AAAI'24).

Additional figures

We provide figures with full legends in figs-with-full-legends/ folder, with additional examples of Figure 5.

Dataset preparation

Put the DomainNet dataset under dataset/.

Source pretrained weights

Download pretrained source models here. Decompress and put it under main directory.

Necessary packages

  • python==3.8
  • pytorch==1.13
  • timm
  • termcolor
  • Apex
git clone https://github.com/NVIDIA/apex
cd apex
pip install -v --disable-pip-version-check --no-cache-dir ./
https://github.com/NVIDIA/apex/issues/1227

How to run

Run by bash run.sh. Logs are under my/.

Key files

main.py contains main training code, and models/model.py contains model design.

Acknowledgements

Our code is based on PMTrans. Thanks for their great work!

About

PyTorch implementation of AAAI2024 paper Agile Multi-Source-Free Domain Adaptation

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published