search

caizhongang / SMPLer-X

Official Code for "SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation"
https://caizhongang.github.io/projects/SMPLer-X/
Other
1.01k stars 73 forks source link

Image normalization and VIT #31

Closed GhostLate closed 7 months ago

GhostLate commented 1 year ago

I noticed, that there is only one transform: ToTensor() in the DataLoader. Why don't you use image normalization (mean, std) before first VIT's layers?

caizhongang commented 11 months ago

Hi @GhostLate , we follow OSX in training the transformer backbones. We didn't conduct extensive experiments on training details. However, some tuning here and there may be useful.