You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
gaoyang Tang 0ed31318fe commit setup, version and docs. 3 weeks ago
READ_mindspore commit setup, version and docs. 3 weeks ago
docs commit setup, version and docs. 3 weeks ago
examples Initial commit 3 weeks ago
.gitignore Initial commit 3 weeks ago
LICENSE Initial commit 3 weeks ago
README.md Update README 3 weeks ago
requirements.txt commit setup, version and docs. 3 weeks ago
setup.py commit setup, version and docs. 3 weeks ago

README.md


READ (Reconstruction or Embedding based Anomaly Detection)

This repo is the mindspore version of READ, plz jump to https://git.openi.org.cn/OpenI/READ_pytorch for the pytorch version.

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

  • [Nov 07 2021] READ_mindspore v0.1.0 is Released!
    Please refer to ChangeLog for details and release history.

Installation

Install the latest version from the master branch on OpenI

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

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 SPADE-R50 PaDiM-R50 STPM-R18
Carpet 0.908 0.998 0.970
Grid 0.783 0.927 0.944
Leather 0.980 1.0 0.999
Tile 0.939 0.986 0.981
Wood 0.985 0.998 0.990
All texture classes 0.919 0.982 0.977
Bottle 0.999 1.0 1.0
Cable 0.795 0.978 0.921
Capsule 0.897 0.902 0.777
Hazelnut 1.0 0.945 0.998
Metal nut 0.980 0.987 0.998
Pill 0.855 0.947 0.942
Screw 0.929 0.844 0.774
Toothbrush 0.958 0.964 0.922
Transistor 0.868 0.993 0.907
Zipper 0.870 0.859 0.949
All object classes 0.915 0.942 0.919
All classes 0.916 0.955 0.938
  • Pixel-level anomaly detection accuracy (ROCAUC)
MVTec SPADE-R50 PaDiM-R50 STPM-R18
Carpet 0.985 0.982 0.988
Grid 0.976 0.958 0.975
Leather 0.992 0.987 0.992
Tile 0.938 0.936 0.962
Wood 0.955 0.942 0.957
All texture classes 0.969 0.961 0.975
Bottle 0.975 0.980 0.983
Cable 0.944 0.980 0.944
Capsule 0.988 0.984 0.966
Hazelnut 0.992 0.981 0.988
Metal nut 0.979 0.965 0.946
Pill 0.954 0.973 0.974
Screw 0.993 0.984 0.975
Toothbrush 0.991 0.987 0.988
Transistor 0.839 0.981 0.808
Zipper 0.978 0.978 0.984
All object classes 0.963 0.979 0.956
All classes 0.965 0.973 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!

简介

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。

Python other

贡献者 (2)