gitpulse

lucidrains/vit-pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

25,578 星标3,496 复刻PythonMIT推送于 2026-11-07

在 GitHub 上查看 →

星标动能

今日+2 (+0.0%)
本周+15 (+0.1%)
本月+26 (+0.1%)

主题

artificial-intelligenceattention-mechanismtransformerscomputer-visionimage-classification