基础:
https://zhuanlan.zhihu.com/p/53010734
attention讲解
https://zhuanlan.zhihu.com/p/48508221
transerformer讲解
https://www.jianshu.com/p/e6b5b463cf7b
Embedding细节讲解
https://www.jianshu.com/p/81901d3d3f8e
Encoder细节讲解
https://www.bilibili.com/video/BV1uK411L7nt?from=search&seid=13211796835588968686
bert视频讲解(选看)
transerformer in cv
https://zhuanlan.zhihu.com/p/266311690
vit论文讲解
https://www.bilibili.com/video/av457380431/
vit论文讲解(没看)
https://www.bilibili.com/video/av838282036
Dert论文讲解
https://www.jianshu.com/p/73433766ad2f
Dert代码讲解
Bottleneck Transformers for Visual Recognition
transerfomer应用于主干网络
https://mp.weixin.qq.com/s/LE0WvOc9PDkV5qC9L0qskw
T2T-ViT讲解