Vision Transformer - Pytorch
在 Pytorch 中实现 Vision Transformer，这是一种在视觉分类中实现 SOTA 的简单方法，只需使用单个 transformer 编码器。「Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch.」
Main metrics
Overview
| Name With Owner | lucidrains/vit-pytorch |
|---|---|
| Primary Language | Python |
| Program language | Python (Language Count: 1) |
| Platform | Linux, Mac, Windows |
| License: | MIT License |
| Release Count | 238 |
| Last Release Name | 1.14.5 (Posted on ) |
| First Release Name | 0.0.1 (Posted on ) |
| Created At | 2020-10-03 22:47:24 |
| Pushed At | 2025-10-24 21:00:44 |
| Last Commit At | |
| Stargazers Count | 24259 |
| Watchers Count | 158 |
| Fork Count | 3417 |
| Commits Count | 359 |
| Has Issues Enabled | |
| Issues Count | 274 |
| Issue Open Count | 130 |
| Pull Requests Count | 38 |
| Pull Requests Open Count | 12 |
| Pull Requests Close Count | 11 |
| Has Wiki Enabled | |
| Is Archived | |
| Is Fork | |
| Is Locked | |
| Is Mirror | |
| Is Private |
