search

yan-hao-tian / VW

iclr2024 poster Varying Window Attention
MIT License
114 stars 19 forks source link

Train code #7

Closed jk222414 closed 2 months ago

jk222414 commented 1 year ago

Hello, I am really impressed with Lawin Transformer. I would like to train with the model you proposed, but there are difficulties because hyper-parameters related to learning are not shared in the paper Could you please share the code to train it? thank you

yan-hao-tian commented 1 year ago

Hello, the code can be trained now.