lukasruff/Deep-SVDD-PyTorch

A PyTorch implementation of the Deep SVDD anomaly detection method

51
/ 100
Established

This project helps identify unusual or 'anomalous' items within a dataset, like finding a counterfeit bill in a stack of legitimate currency or a faulty sensor reading among normal ones. It takes a collection of data samples, such as images or numerical readings, and outputs an 'anomaly score' for each, indicating how unusual it is. This is ideal for quality control specialists, fraud detection analysts, or anyone who needs to automatically flag rare or out-of-place data points.

779 stars. No commits in the last 6 months.

Use this if you need to detect anomalies or outliers in your datasets, especially with image data, by training a model solely on 'normal' examples.

Not ideal if you have a dataset with many known types of anomalies and want to classify them into specific categories, rather than just identifying them as unusual.

anomaly-detection fraud-detection quality-control fault-detection outlier-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

779

Forks

210

Language

Python

License

MIT

Last pushed

Dec 08, 2022

Commits (30d)

0

Get this data via API

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

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