search

frgfm / Holocron

PyTorch implementations of recent Computer Vision tricks (ReXNet, RepVGG, Unet3p, YOLOv4, CIoU loss, AdaBelief, PolyLoss, MobileOne). Other additions: AdEMAMix
https://frgfm.github.io/Holocron/latest
Apache License 2.0
319 stars 49 forks source link

feat(optim): add support of AdEMAMix optimizer #373

Closed frgfm closed 1 month ago

frgfm commented 1 month ago

This PR adds support for AdEMAMix optimizer, as detailed in the paper https://arxiv.org/pdf/2409.03137