Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

ML Transformer Vision #226

Open
junxnone opened this issue Jan 27, 2021 · 1 comment
Open

ML Transformer Vision #226

junxnone opened this issue Jan 27, 2021 · 1 comment

Comments

@junxnone
Copy link
Owner

junxnone commented Jan 27, 2021

Transformer 在视觉方面的应用

Reference

Brief

  • Classification

CNN Vs Transformer

CNN Vs Transformer 不同点
CNN 参数共享, Local 信息聚合
Transformer 全局感受野, Global 信息聚合
Name Description CNN Transformer
ViT
DETR
BoTNet
T2T-ViT
DeiT

Classification

Models

  • ViT
  • T2T-ViT
  • DeiT
  • W/ Efficient Attention
    • Linformer
    • Routing Transformer
    • Sinkhorn Transformer
    • Nystromformer

OpenSource Code

  • timm release with pretrained weight
  • vit-pytorch
    • module
      • vit_pytorch => vanilla vit
      • distill
        • DistillableViT
      • t2t
        • T2TViT
      • efficient => 自定义的 Transformer module
        • Linformer
        • Nystromformer
@junxnone
Copy link
Owner Author

#212

@junxnone junxnone changed the title Jan 20, 2022
@junxnone junxnone transferred this issue from junxnone/tio Jan 20, 2022
@junxnone junxnone changed the title Transformer Vision ML Transformer Vision Dec 24, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant