pyod and pytorch-ood
These are complementary tools where PyOD provides general-purpose outlier detection across multiple algorithms while PyTorch-OOD specializes in out-of-distribution detection specifically for deep learning models, allowing practitioners to use both for different detection scenarios in a single pipeline.
About pyod
yzhao062/pyod
A Python Library for Outlier and Anomaly Detection, Integrating Classical and Deep Learning Techniques
Provides 45+ detection algorithms unified under a scikit-learn compatible API, combining classical methods (LOF, Isolation Forest) with 12 PyTorch-based neural models. Emphasizes performance through Numba JIT compilation and the SUOD framework for fast training/prediction, plus LLM-guided automated model selection to reduce manual hyperparameter tuning.
About pytorch-ood
kkirchheim/pytorch-ood
👽 Out-of-Distribution Detection with PyTorch
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work