search

fudan-zvg / SETR

[CVPR 2021] Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
MIT License
1.05k stars 149 forks source link

21k Pretrain weight #28

Closed xiexinch closed 3 years ago

xiexinch commented 3 years ago

Could you please release the ResNet101 pretrained weights with ImageNet21K or tell us where can we find it? Thank you!

lzrobots commented 3 years ago

Hi I think the ViT paper does provide those weights.

xiexinch commented 3 years ago

Hi @lzrobots Sorry for bothering you, I have searched the official ViT repo, but I can't find the weights.. https://github.com/google-research/vision_transformer/issues/36 https://github.com/google-research/big_transfer/issues/21 Could you please provide a link?

lzrobots commented 3 years ago

you might get the weights from the readme file of the BiT repo you mentioned above.