Skip to content

Latest commit

 

History

History
39 lines (31 loc) · 1.08 KB

README.md

File metadata and controls

39 lines (31 loc) · 1.08 KB

Bagel

The implementation of 'Robust and Unsupervised KPI Anomaly Detection Based on Conditional Variational Autoencoder' Models are in model.py.

The module threshold_selection is missed. You can replace it with a self-defined threshold.

Dependencies

python >= 3.7

pip install -r requirements.txt

Note: Torch requires a manual download (make sure it's version 0.4)

Run

python main.py

For the sample code

python competition.py

For the comp code

Citation

Li, Zeyan, Wenxiao Chen, and Dan Pei. "Robust and Unsupervised KPI Anomaly Detection Based on Conditional Variational Autoencoder." 2018 IEEE 37th International Performance Computing and Communications Conference (IPCCC). IEEE, 2018.

@inproceedings{li2018robust,
  title={Robust and Unsupervised KPI Anomaly Detection Based on Conditional Variational Autoencoder},
  author={Li, Zeyan and Chen, Wenxiao and Pei, Dan},
  booktitle={2018 IEEE 37th International Performance Computing and Communications Conference (IPCCC)},
  pages={1--9},
  year={2018},
  organization={IEEE}
}