LeapLabTHU/
1.5−3.0× lossless training or pre-training speedup. An off-the-shelf, easy-to-implement algorithm for the efficient training of foundation visual backbones.
by LeapLab Python MIT licence 9 forks Created Nov 2022 View on GitHub
- Stars
- 233
- 2% of LeapLabTHU's stars
- Rank
- #243,373
- of 847,120 repos, top 29%
- In Python
- #47,166
- of 172,217 repos, top 28%
Among 847,120 repos
160–250 stars: 103,728 repos, including EfficientTrain
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 #242,522
- Next milestone
- +123 stars to reach the top 20%
- Popular
- One of 488,400 repos with 100+ stars
- Yearly average
- 58 stars a year since Nov 2022