• python == 3.7.13
• cudatoolkit == 10.1.243
• pytorch ==1.7.1
• torchvision == 0.8.2
• numpy, scikit-learn, PIL, argparse

• Configure the PyTorch environment.
• Download the Office-Home dataset. Configure the data lists in data and the checkpoints in ckpts.
• Run the code in mixval_run0.sh.

@inproceedings{hu2023mixed,
    title={Mixed Samples as Probes for Unsupervised Model Selection in Domain Adaptation},
    author={Dapeng Hu and Jian Liang and Jun Hao Liew and Chuhui Xue and Song Bai and Xinchao Wang},
    booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
    year={2023}
}

• [email protected]