lukasruff/Deep-SAD-PyTorch

A PyTorch implementation of Deep SAD, a deep Semi-supervised Anomaly Detection method.

50
/ 100
Established

This project helps data scientists or machine learning engineers identify rare, unusual, or suspicious data points in large datasets. It takes a mix of labeled (known normal or abnormal) and unlabeled data to build a model that can flag anomalies. The output is a method to detect these unusual patterns, even with very little initial labeled information.

351 stars. No commits in the last 6 months.

Use this if you need to detect anomalies in complex, high-dimensional datasets and have a small amount of labeled examples (both normal and anomalous) to guide the detection process.

Not ideal if you have no labeled data at all, or if your anomaly detection needs are simple and can be met with traditional, less computationally intensive methods.

fraud-detection quality-control cybersecurity-monitoring medical-diagnosis predictive-maintenance
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

351

Forks

100

Language

Python

License

MIT

Last pushed

Nov 22, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/lukasruff/Deep-SAD-PyTorch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.