Skip to content

This is official implementation for annealed Winner-Takes-All loss in <Annealed Winner-Takes-All for Motion Forecasting>.

Notifications You must be signed in to change notification settings

valeoai/MF_aWTA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 

Repository files navigation

Annealed Winner-Takes-All for Motion Forecasting

This is official implementation for annealed Winner-Takes-All loss presented in this work. Work under review, the code will be released soon.



annealed Winner-Takes-All (aWTA), a better loss for training motion forecasting models:

About

This is official implementation for annealed Winner-Takes-All loss in <Annealed Winner-Takes-All for Motion Forecasting>.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published