rasbt/comparing-automatic-augmentation-blog
Comparing four automatic image augmentation techniques in PyTorch: AutoAugment, RandAugment, AugMix, and TrivialAugment
This project helps machine learning practitioners improve the performance of their image classification models by comparing four different automatic image augmentation techniques. It takes an existing image dataset and applies various transformations, outputting a clear comparison of how each method impacts model accuracy. Data scientists and machine learning engineers working with image data would find this useful.
No commits in the last 6 months.
Use this if you are developing computer vision models and want to understand which automated image augmentation strategy will most effectively boost your model's accuracy on image classification tasks.
Not ideal if you need a specific, custom image augmentation pipeline, or if you are not working with image data.
Stars
31
Forks
—
Language
Jupyter Notebook
License
BSD-3-Clause
Category
Last pushed
Feb 07, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/rasbt/comparing-automatic-augmentation-blog"
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