Transformer
Transformer 是 Google 的团队在 2017 年提出的一种 NLP 经典模型，现在比较火热的 Bert 也是基于 Transformer。Transformer 模型使用了 Self-Attention 机制，不采用 RNN 的顺序结构，使得模型可以并行化训练，而且能够拥有全局信息。
==== |
====== |
========= |
======= |
===== |
==== |
==== |
==== |
======= |
======= |
============ |
==========
Transformers
==========
| Transformers |
Swin-Transformer |
video-swin-transformer-pytorch |
Transformer-SSL |
Swin-Transformer-Semantic-Segmentation |
swin-mlp |
| transformer-pytorch |
vision_transformer |
vit-pytorch |
Awesome-Visual-Transformer |