asyml / vision-transformer-pytorch

Pytorch version of Vision Transformer (ViT) with pretrained models. This is part of CASL (https://casl-project.github.io/) and ASYML project.

Home Page:https://asyml.io/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

R50+ViT-B/16 hybrid model ?

GuHongyang opened this issue · comments

I found that Google has updated the R50+ViT-B/16 hybrid model. Can the pytorch version also be updated?

We have provided the PyTorch version of the code and pre-trained model in https://github.com/tczhangzhi/VisionTransformer-Pytorch. If the authors have no other plans, we are glad to make PR to this repo. You can currently use R50+ViT-B in the following ways:

from vision_transformer_pytorch import VisionTransformer

net = VisionTransformer.from_pretrained('R50+ViT-B_16')

Thank you! Could you make a PR to the repo?