KaiyangZhou / pytorch-center-loss

Pytorch implementation of Center Loss
MIT License
970 stars 219 forks source link

Center loss in small batch multiclass training #27

Open SuperbTUM opened 1 year ago

SuperbTUM commented 1 year ago

Hello authors and contributors of center loss, thanks for the impressive work. I got a question as I noticed the center update is based on each mini-batch, and if I had a small batch and many classes (way more than batch size), the center update may become tricky, and I wonder if using momentum or other optimizers is necessary for training. Thanks.