基于TCL在智能制造上缺陷检测的成功经验,TCL集团工业研究院开源了第一个工业视觉无监督异常检测框架,具有算法丰富、开箱即用、精度保证等特点。
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
tcl-read-maintainer f5c40475da Update README 1 month ago
READ_pytorch Initial commit 1 month ago
docs Update installation 1 month ago
examples Initial commit 1 month ago
.gitignore Update License 1 month ago
LICENSE Initial commit 1 month ago
README.md Update README 1 month ago
requirements.txt Update License 1 month ago
setup.py Initial commit 1 month ago

README.md


READ (Reconstruction or Embedding based Anomaly Detection)

READ is an open source toolbox focused on unsupervised anomaly detection/localization tasks. By only training on the defect-free samples, READ is able to recognize defect samples or even localize anomalies on defect samples.

The purpose of this repo is to promote the research and application of unsupervised anomaly detection and localization algorithms. READ is designed to provide:

  • A unified interface for encapsulating diverse anomaly localization algorithms
  • High quality implementations of novel anomaly localization algorithms
  • Templates for using these algorithms in a detailed task

In addition, READ provides the benchmarks for validating novel unsupervised anomaly detection and localization algorithms for MVTec AD dataset.

Changelog

  • [May 08 2021] READ v0.1.0 is Released!

Installation

Install the latest version from the master branch on OpenI

pip install -U git+https://git.openi.org.cn/OpenI/READ_pytorch

Please follow the Installation document to get a detailed instruction.

Getting Started

Please follow the Getting Started document to run the provided demo tasks.

Localization examples (based on READ)

Supported Algorithms

Results

Implementation results on MVTec

  • Image-level anomaly detection accuracy (ROCAUC)
MVTec RIAD FAVAE SPADE-WR50X2 PaDiM-WR50X2 USTAD STPM
Carpet 0.654 0.642 0.819 0.996 0.886 0.844
Grid 0.980 1.000 0.42 0.966 0.919 0.982
Leather 0.982 0.706 0.94 1.000 0.748 0.989
Tile 0.838 0.842 0.980 0.973 0.998 0.981
Wood 0.861 0.879 0.979 0.987 0.952 0.997
All texture classes 0.863 0.814 0.828 0.984 0.901 0.959
Bottle 0.984 0.999 0.972 0.999 0.940 1.000
Cable 0.543 0.942 0.857 0.880 0.478 0.874
Capsule 0.836 0.712 0.873 0.896 0.785 0.911
Hazelnut 0.904 0.999 0.907 0.950 0.939 0.986
Metal nut 0.820 0.911 0.734 0.987 0.509 0.988
Pill 0.789 0.779 0.785 0.935 0.798 0.982
Screw 0.746 0.595 0.658 0.846 0.706 0.871
Toothbrush 0.956 0.925 0.878 0.981 0.825 0.769
Transistor 0.890 0.885 0.900 0.983 0.563 0.810
Zipper 0.978 0.647 0.952 0.920 0.761 0.967
All object classes 0.845 0.839 0.852 0.9377 0.730 0.916
All classes 0.851 0.831 0.844 0.953 0.787 0.930
  • Pixel-level anomaly detection accuracy (ROCAUC)
MVTec RIAD FAVAE SPADE-WR50X2 PaDiM-WR50X2 USTAD STPM
Carpet 0.904 0.836 0.985 0.988 0.958 0.977
Grid 0.984 0.994 0.978 0.969 0.850 0.983
Leather 0.990 0.908 0.993 0.991 0.914 0.991
Tile 0.761 0.626 0.942 0.940 0.948 0.969
Wood 0.821 0.908 0.956 0.946 0.899 0.940
All texture classes 0.892 0.854 0.971 0.967 0.914 0.972
Bottle 0.945 0.962 0.968 0.982 0.902 0.983
Cable 0.619 0.957 0.920 0.957 0.816 0.940
Capsule 0.978 0.965 0.983 0.985 0.913 0.973
Hazelnut 0.974 0.987 0.986 0.982 0.974 0.968
Metal nut 0.828 0.953 0.969 0.972 0.891 0.954
Pill 0.955 0.943 0.947 0.950 0.928 0.987
Screw 0.984 0.960 0.992 0.984 0.967 0.983
Toothbrush 0.966 0.984 0.989 0.988 0.947 0.982
Transistor 0.813 0.907 0.861 0.973 0.687 0.806
Zipper 0.981 0.817 0.982 0.983 0.825 0.987
All object classes 0.904 0.944 0.960 0.976 0.885 0.956
All classes 0.900 0.914 0.963 0.973 0.895 0.962

License

This project is released under the Open-Intelligence Open Source License V1.1.

Contact

Please contact me if there is any question (Chao Zhang chao.zhang46@tcl.com).

About

Machine Vision Group, TCL Corporate Research(HK) Co., Ltd is the main developer of READ.

Any contributions to READ is welcome!