Kevinz-code / CSRA

Official code of ICCV2021 paper "Residual Attention: A Simple but Effective Method for Multi-Label Recognition"
GNU Affero General Public License v3.0
210 stars 37 forks source link

How to use VIT-224 pretrain weight with 448 input size #22

Closed zizizihua closed 1 year ago

zizizihua commented 1 year ago

Thanks for your excellent work! I noticed you use VIT-L16-224 to train on coco,with an input size of 448. May I ask how to use VIT-224 pretrain weight with 448 input size?