search

Liangqiong / ViT-FL-main

MIT License
100 stars 18 forks source link

ViT(T) and ViT(S) #8

Open alessiomora opened 11 months ago

alessiomora commented 11 months ago

Hi, thank you for your nice paper.

What is the original paper of ViT(T) and ViT(S)? In my opinion, this is unclear both in the code and in your paper. Is it from [1]?

Thank you.

[1] Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Hervé Jégou. Training data-efficient image transformers & distillation through attention. arXiv:2012.12877, 2020.

Liangqiong commented 6 months ago

https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/vision_transformer.py Pretrained model and code is from the above link.