---
license: mit
metrics:
- accuracy
---

# Tiny-ImageNet-ResNet

<!-- Provide a quick summary of what the model is/does. -->

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

<!-- Provide the basic links for the model. -->

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


### Downstream Use

<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->

- **Dataset Distillation**:
[SRe<sup>2</sup>L](https://github.com/VILA-Lab/SRe2L) distilled Tiny-ImageNet images from these models


## Training Details

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


## Evaluation


## Citation

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

```
@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](https://huggingface.co./zeyuanyin)

## Model Card Contact

yinzeyuan1037@gmail.com