Why there is "no_weight_decay" function for Swin-T but not for VIT
TongZhangTHU opened this issue · 0 comments
TongZhangTHU commented
Hi, I am wondering, why in "simmim.py", there is "no_weight_decay" function for "class SwinTransformerForSimMIM", but not for "class VisionTransformerForSimMIM" ?