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
This helps data analysts and researchers identify unusual or suspicious data points within large, complex datasets. You input your tabular data, and it outputs scores indicating how much each data point deviates from the norm. This is designed for anyone who needs to find anomalies in multivariate data for tasks like fraud detection, quality control, or system monitoring.
About pytorch-ood
kkirchheim/pytorch-ood
👽 Out-of-Distribution Detection with PyTorch
This tool helps machine learning engineers and researchers validate the robustness of their deep neural networks. It takes your trained PyTorch deep learning model and new, potentially unfamiliar data, and then identifies inputs that are 'out-of-distribution' or unexpected. The output is a score for each input, indicating how likely it is to be an outlier, helping you build more reliable AI systems.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work