[HN Gopher] Lessons learned from manually classifying CIFAR-10 (...
___________________________________________________________________
Lessons learned from manually classifying CIFAR-10 (2011)
Author : djoldman
Score : 54 points
Date : 2024-04-09 10:48 UTC (1 days ago)
(HTM) web link (karpathy.github.io)
(TXT) w3m dump (karpathy.github.io)
| 01HNNWZ0MV43FF wrote:
| > The state of the art is currently at about 80% classification
| accuracy
|
| 13 years later, I guess it's around 99% accuracy.
|
| https://en.wikipedia.org/wiki/CIFAR-10#Research_papers_claim...
| karpathy wrote:
| Hah why is this on HN today?
|
| Update from 2024:
|
| https://github.com/tysam-code/hlb-CIFAR10 Train to 94% on
| CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110
| seconds (or less!)
|
| https://paperswithcode.com/sota/image-classification-on-cifa...
| 99.5% SOTA
|
| so that's embarrassing :)
| djoldman wrote:
| I posted it because it was linked to by Keller Jordan:
|
| https://arxiv.org/abs/2404.00498v2
___________________________________________________________________
(page generated 2024-04-10 23:01 UTC)