bflammers / automahalanobis

A PyTorch implementation of an autoencoder trained to minimize the Mahalanobis distance between input and reconstruction.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Mahalanobis autoencoder for anomaly detection

A benchmarking experiment to see if a Mahalanobis autoencoder is better at detecting anomalies than a normal autoencoder.

About

A PyTorch implementation of an autoencoder trained to minimize the Mahalanobis distance between input and reconstruction.


Languages

Language:Python 95.6%Language:Shell 4.4%