e-sensing/torchopt
R implementation of advanced optimizers for torch
This R package provides implementations of advanced optimization algorithms for machine learning models built with the 'torch' package in R. It allows R users to apply a wider range of sophisticated techniques to fine-tune their deep learning models. The end user is an R programmer or data scientist who is building and training deep learning models and wants access to a broader set of optimizers than what 'torch' natively offers.
No commits in the last 6 months.
Use this if you are an R user working with the 'torch' package for deep learning and need to experiment with or apply advanced optimization algorithms like AdamW, AdaBelief, or AdaHessian to improve your model training.
Not ideal if you are not using R or the 'torch' package for deep learning, or if the standard optimizers already available in 'torch' meet your needs.
Stars
26
Forks
5
Language
R
License
—
Category
Last pushed
Jun 08, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/e-sensing/torchopt"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
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.
opthub-org/pytorch-bsf
PyTorch implementation of Bezier simplex fitting
gpauloski/kfac-pytorch
Distributed K-FAC preconditioner for PyTorch
pytorch/xla
Enabling PyTorch on XLA Devices (e.g. Google TPU)