{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","url":"https://codeofpaper.com/paper/2101.11986","arxiv_url":"https://arxiv.org/abs/2101.11986","published":"2021-01-28","code":"official","best":{"full_name":"yitu-opensource/T2T-ViT","url":"https://github.com/yitu-opensource/T2T-ViT","tier":"official","stars":1193,"license":null,"framework":null,"language":"Jupyter Notebook","last_commit":"2023-10-27T19:00:24"},"most_starred_community":null,"implementations":[{"full_name":"yitu-opensource/T2T-ViT","url":"https://github.com/yitu-opensource/T2T-ViT","tier":"official","stars":1193,"license":null,"framework":null,"language":"Jupyter Notebook","last_commit":"2023-10-27T19:00:24"}],"possible_matches":0}