Skip to content

Unoficial FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows

License

Notifications You must be signed in to change notification settings

wuzujiong/FastFlow-AD

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

22 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

FastFlow-AD

image

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.

Image classification AUROC

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"

Image segmentation AUROC

TODO

How to use

python main.py --dataset {root_path} --classname {classname}

Example:

python main.py --dataset ./MVTec --classname bottle

About

Unoficial FastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages