ildoonet/pytorch-randaugment
Unofficial PyTorch Reimplementation of RandAugment.
This project helps machine learning engineers improve the accuracy of their image classification models. By applying a range of automated image transformations (like rotations, shifts, or color adjustments) during training, it allows models to learn from a wider variety of visual data. It takes your existing image datasets and training setup, then outputs a more robust and better-performing image classification model.
638 stars. No commits in the last 6 months.
Use this if you are a machine learning engineer working on image classification and want to boost your model's performance with minimal hyperparameter tuning.
Not ideal if you need to reproduce exact, state-of-the-art results for large-scale ImageNet classification, as some discrepancies have been noted.
Stars
638
Forks
97
Language
Python
License
MIT
Category
Last pushed
Mar 14, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ildoonet/pytorch-randaugment"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TorchIO-project/torchio
Medical imaging processing for AI applications.
aleju/imgaug
Image augmentation for machine learning experiments.
makcedward/nlpaug
Data augmentation for NLP
mdbloice/Augmentor
Image augmentation library in Python for machine learning.
BloodAxe/pytorch-toolbelt
PyTorch extensions for fast R&D prototyping and Kaggle farming