Unoficial implementation of FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows https://arxiv.org/pdf/2111.07677v2.pdf
WIP repo: this code is unfinished. I welcome and appreciate any contributions to the Q&A issue. Whether you want to do a pull request, please make sure that your contribution improves the table.
Avg | Carpet | Grid | Leather | Tile | Wood | Bottle | Cable | Capsule | Hazelnut | Metal Nut | Pill | Screw | Toothbrush | Transistor | Zipper | |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Wide ResNet-50 | TODO | 0.99 | 0.97 | 1.0 | 1.0 | 1.0 | 1.0 | 0.95 | 0.80 | 0.99 | 0.97 | 0.95 | 0.99 | 0.86 | 0.88 | 1.0 |
Note: *We had this results with the "First commit"
TODO
python main.py --dataset {root_path} --classname {classname}
Example:
python main.py --dataset ./MVTec --classname bottle