jettify/pytorch-optimizer
A PyTorch-compatible library providing implementations of 20+ advanced optimization algorithms for deep learning model training.
Not currently ranked — collecting fresh signals.
star history
This repository provides a curated collection of optimization algorithms compatible with PyTorch’s optimizer module. It implements research-grade optimizers including DiffGrad, LAMB, AdaBelief, Adamod, and Lookahead, which are used to train neural networks. Users can swap standard PyTorch optimizers with these alternatives by changing only the import statement and class name, making experimental comparison straightforward.
Frequently asked
- What is jettify/pytorch-optimizer?
- A PyTorch-compatible library providing implementations of 20+ advanced optimization algorithms for deep learning model training.
- Is pytorch-optimizer open source?
- Yes — jettify/pytorch-optimizer is open source, released under the Apache-2.0 license.
- What language is pytorch-optimizer written in?
- jettify/pytorch-optimizer is primarily written in Python.
- How popular is pytorch-optimizer?
- jettify/pytorch-optimizer has 3.2k stars on GitHub.
- Where can I find pytorch-optimizer?
- jettify/pytorch-optimizer is on GitHub at https://github.com/jettify/pytorch-optimizer.