Pytorch implementation of Single Domain Generalization via Diversity Probe.

• Linux
• Python 3.8
• Pytorch 1.8.0
• Torchvision 0.9.0
• NVIDIA GPU + CUDA CuDNN

Note: You need to download the data if you wish to train your own model.

Download the digits dataset from this link[BaiDuYunDisk] and its extracted code: xcl3. Please extract it inside the data directory

cd data
unzip digits.zip
cd ..

Pretrained task model is available at this link[BaiDuYunDisk] and its extracted code:dp46. Download and extract it in the models_pth directory.

In runDivPro.py:

• Specify the output directory to save the results in --dir.
• Turn on the evaluation in--eval
• Run python runDivPro.py --dir SAVE_DIR --eval True

• Specify the output directory to save the results in --dir.
• Run python runDivPro.py --dir SAVE_DIR

We thank the following authors for releasing their source code, data and models:

• Progressive Domain Expansion Network for Single Domain Generalization
• Learning to Diversify for Single Domain Generalization