Example scripts support all models in PyTorch-Image-Models. You also need to install timm to use PyTorch-Image-Models.
pip install timm
Following datasets can be downloaded automatically:
Supported methods include:
- Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net (IBN-Net, 2018 ECCV)
- Domain Generalization with MixStyle (MixStyle, 2021 ICLR)
The shell files give the script to reproduce the benchmarks with specified hyper-parameters. For example, if you want to reproduce MixStyle on Market1501 -> DukeMTMC task, use the following script
# Train MixStyle on Market1501 -> DukeMTMC task using ResNet 50.
# Assume you have put the datasets under the path `data/market1501` and `data/dukemtmc`,
# or you are glad to download the datasets automatically from the Internet to this path
CUDA_VISIBLE_DEVICES=0 python mixstyle.py data -s Market1501 -t DukeMTMC -a resnet50 \
--mix-layers layer1 layer2 --finetune --seed 0 --log logs/mixstyle/Market2DukeFor more information please refer to Get Started for help.
If you use these methods in your research, please consider citing.
@inproceedings{IBN-Net,
author = {Xingang Pan, Ping Luo, Jianping Shi, and Xiaoou Tang},
title = {Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net},
booktitle = {ECCV},
year = {2018}
}
@inproceedings{mixstyle,
title={Domain Generalization with MixStyle},
author={Zhou, Kaiyang and Yang, Yongxin and Qiao, Yu and Xiang, Tao},
booktitle={ICLR},
year={2021}
}