Kedreamix/
MAE for CIFAR，由于可用资源有限，我们仅在 cifar10 上测试模型。我们主要想重现这样的结果：使用 MAE 预训练 ViT 可以比直接使用标签进行监督学习训练获得更好的结果。这应该是自我监督学习比监督学习更有效的数据的证据。
by Kedreamix Jupyter Notebook MIT licence 8 forks Created Apr 2023 View on GitHub
- Stars
- 84
- 1% of Kedreamix's stars
- Rank
- #557,763
- of 851,979 repos, top 66%
- In Jupyter Notebook
- #13,343
- of 21,672 repos, top 62%
Among 851,979 repos
63–100 stars: 217,619 repos, including MAE-for-CIFAR
top 50%top 10%top 1%top 0.1% 
Stars along the bottom, and repos in each band on a log scale
Quick stats
- Next rank
- +1 star to reach #552,543
- Next milestone
- +10 stars to reach the top 60%
- Yearly average
- 24 stars a year since Apr 2023