hendrycks/robustness
Corruption and Perturbation Robustness (ICLR 2019)
This project helps machine learning engineers and researchers evaluate how robust their image classification models are when faced with common real-world image distortions like blur, noise, or adverse weather conditions. You provide your trained neural network model, and it outputs detailed metrics showing how well the model performs under various corruptions and perturbations. This is ideal for anyone developing or deploying computer vision systems, especially in critical applications where image quality might be unpredictable.
1,139 stars. No commits in the last 6 months.
Use this if you need to rigorously test your image classification model's reliability against common real-world image corruptions and perturbations.
Not ideal if you are looking for a tool to train or fine-tune your model, as this project focuses specifically on evaluation.
Stars
1,139
Forks
151
Language
Python
License
Apache-2.0
Category
Last pushed
Aug 24, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/hendrycks/robustness"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
namkoong-lab/dro
A package of distributionally robust optimization (DRO) methods. Implemented via cvxpy and PyTorch
neu-autonomy/nfl_veripy
Formal Verification of Neural Feedback Loops (NFLs)
THUDM/grb
Graph Robustness Benchmark: A scalable, unified, modular, and reproducible benchmark for...
MinghuiChen43/awesome-trustworthy-deep-learning
A curated list of trustworthy deep learning papers. Daily updating...
ADA-research/VERONA
A lightweight Python package for setting up robustness experiments and to compute robustness...