PyTorch-DAGMM
This is my Minimal PyTorch implementation for Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection (DAGMM, ICLR 2018)
Results
This implementation achieves similar results as the original paper.
KDD99Cup:
| Precision | Recall | F1-score | |
|---|---|---|---|
| Paper | 0.9297 | 0.9442 | 0.9369 |
| This Implementation | 0.9486 | 0.9196 | 0.9325 |