For Unsupervised Domain Adaptation: A Game Perspective
- Download swin_base_patch4_window7_224_22k.pth and put it into
pretrained_models
- Create a conda virtual environment and activate it:
conda env create -f environment.yml
- Install
Apex
:
git clone https://github.com/ptrblck/apex
cd apex
pip install -v --disable-pip-version-check --no-cache-dir ./
- Download the
Office31, Office Home, VisDA and Domainnet
Make a file recording the path and label of image like txt files indatasets/office_home/
$ tree data
datasets
├── ofice_home
│ ├── Art.txt
│ ├── Clipart.txt
│ ├── Product.txt
│ ├── Real_World.txt
└── ...
https://github.com/jindongwang/transferlearning/blob/master/data/dataset.md
bash dist_train.sh