Giters

jeonsworld / ViT-pytorch

Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Request for pre-trained weights only on Imagenet2012.

JingyeChen opened this issue · comments

commented

Thanks for your hard work! I wonder if there are some pre-trained weights only using Imagenet2012? I found that the pre-trained ResNet provided by torchvision may be pre-trained only on Imagenet2012 so I want to take ViT and ResNet for a fair comparison.

commented

Unfortunately, the weights for pre-training in imagenet2012 were not disclosed.
Currently published weights are pretrained-imagenet21k, pretrained-imagenet21k and finetuned-imagenet2012.

commented

I got it. Thank you for your reply :D