nanowell/AdEMAMix-Optimizer-Pytorch

The AdEMAMix Optimizer: Better, Faster, Older.

/ 100

Emerging

This project helps machine learning engineers and researchers improve the training process of their neural networks. By taking your existing network and training data, it outputs a more efficiently trained model, potentially achieving better performance in less time. It's for anyone building or experimenting with deep learning models who wants to optimize their training routines.

186 stars. No commits in the last 6 months.

Use this if you are training deep learning models and want to achieve better performance, faster convergence, or more stable training outcomes.

Not ideal if you are looking for a pre-trained model or a tool for data preprocessing rather than training optimization.

deep-learning-training neural-network-optimization machine-learning-research model-performance algorithm-development

Stale 6m No Package No Dependents

Maintenance 0 / 25

Adoption 10 / 25

Maturity 16 / 25

Community 10 / 25

How are scores calculated?

Stars

186

Forks

Language

Python

License

MIT

Higher-rated alternatives

nschaetti/EchoTorch

A Python toolkit for Reservoir Computing and Echo State Network experimentation based on...

metaopt/torchopt

TorchOpt is an efficient library for differentiable optimization built upon PyTorch.

gpauloski/kfac-pytorch

Distributed K-FAC preconditioner for PyTorch

opthub-org/pytorch-bsf

PyTorch implementation of Bezier simplex fitting

pytorch/xla

Enabling PyTorch on XLA Devices (e.g. Google TPU)

Explore ML Frameworks

All categories Trending ML Framework directory Insights