Tiny-ImageNet-ResNet

This project expends torchvision to support training on Tiny-ImageNet. Code is based on the official implementation for image classification in torchvision: https://github.com/pytorch/vision/tree/main/references/classification

Model Details

Model Sources

• Repository: https://github.com/zeyuanyin/tiny-imagenet

Downstream Use

• Dataset Distillation: SRe²L distilled Tiny-ImageNet images from these models

Training Details

https://github.com/zeyuanyin/tiny-imagenet/tree/main#training

Evaluation

Citation

@inproceedings{yin2023sre2l,
    title={Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective},
    author={Yin, Zeyuan and Xing, Eric and Shen, Zhiqiang},
    booktitle={Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)},
    year={2023}
}

Model Card Author

@zeyuanyin

Model Card Contact

yinzeyuan1037@gmail.com