spencerbraun/anomaly_transformer_pytorch

PyTorch implementation of Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy

48
/ 100
Emerging

This helps operations engineers and data analysts detect unusual patterns or outliers in their time-series data. It takes in historical time-series datasets, like server logs or sensor readings, and identifies points in time that deviate significantly from expected behavior. The output highlights these anomalies, helping users proactively address issues or investigate unexpected events.

252 stars. No commits in the last 6 months.

Use this if you need to automatically spot unusual spikes, dips, or other irregular activities in continuous data streams from sensors, IT systems, or financial markets.

Not ideal if your data is not time-series based, or if you need to predict future values rather than just detect current anomalies.

operations-monitoring sensor-data-analysis system-health fraud-detection predictive-maintenance
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

252

Forks

56

Language

Jupyter Notebook

License

MIT

Last pushed

Jan 24, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/spencerbraun/anomaly_transformer_pytorch"

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