https://github.com/yitu-opensource/T2T-ViT

ICCV2021, Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
https://github.com/yitu-opensource/T2T-ViT

t2t-transformer vision-transformer vit

Last synced: 30 days ago
JSON representation

ICCV2021, Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet

• Host: GitHub
• URL: https://github.com/yitu-opensource/T2T-ViT
• Owner: yitu-opensource
• License: other
• Created: 2021-01-23T02:59:09.000Z (almost 4 years ago)
• Default Branch: main
• Last Pushed: 2023-10-27T19:00:24.000Z (about 1 year ago)
• Last Synced: 2024-08-03T20:15:50.782Z (4 months ago)
• Topics: t2t-transformer, vision-transformer, vit
• Language: Jupyter Notebook
• Homepage:
• Size: 15.1 MB
• Stars: 1,133
• Watchers: 18
• Forks: 176
• Open Issues: 21
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-image-classification - official-pytorch: https://github.com/yitu-opensource/T2T-ViT
• awesome_vision_transformer - code
• awesome_vision_transformer - code