gradient-centralization topic

optimizer & lr scheduler & loss function collections in PyTorch

kozistr

Instantly improve your training performance of TensorFlow models with just 2 lines of code!

Rishit-dagli

A New Optimization Technique for Deep Neural Networks

Yonghongwei

Multi-label classification based on timm.

yang-ruixin

Quasi Hyperbolic Rectified DEMON Adam/Amsgrad with AdaMod, Gradient Centralization, Lookahead, iterative averaging and decorrelated Weight Decay

JRC1995

Multi-label classification based on timm, and add SimCLR to timm.

yang-ruixin