Metadata-Version: 2.1
Name: READ-pytorch
Version: 0.1.1
Summary: Unsupervised Anomaly Localization Toolbox and Benchmark
Home-page: https://git.openi.org.cn/OpenI/READ_pytorch
Author: TCL MV Lab
Author-email: chao46.zhang@tcl.com
License: Apache License 2.0
Platform: UNKNOWN
Classifier: Development Status :: 3 - Alpha
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Requires-Python: >=3, <4
Description-Content-Type: text/markdown
Requires-Dist: tqdm
Requires-Dist: numpy
Requires-Dist: pandas
Requires-Dist: scipy
Requires-Dist: timm (>=0.4.5)
Requires-Dist: adabelief-pytorch (>=0.2.0)
Requires-Dist: kornia (>=0.5.0)
Requires-Dist: matplotlib (>=3.3.4)
Requires-Dist: albumentations (==0.5.2)
Requires-Dist: einops (>=0.3.0)
Requires-Dist: scikit-learn (>=0.24.2)
Requires-Dist: scikit-image (>=0.17.2)
Requires-Dist: torch (>=1.7.0)
Requires-Dist: torchvision

<div align="center">
  <img src="docs/img/READlogo.png" width="650"/>
</div>

---
# READ (Reconstruction or Embedding based Anomaly Detection)
This repo is the pytorch version of READ, plz jump to <https://git.openi.org.cn/OpenI/READ_mindspore> for the mindspore 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](https://www.mvtec.com/company/research/datasets/mvtec-ad/).

## Changelog
- **[Nov 07 2021] READ_pytorch v0.1.1 is Released!** 
- **[May 08 2021] READ_pytorch v0.1.0 is Released!**  
Please refer to [ChangeLog](docs/changelog.md) 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_pytorch
```
Please follow the [Installation](docs/installation.md) document to get a detailed instruction.

## Getting Started
Please follow the [Getting Started](docs/getting_started.md) document to run the provided demo tasks.

## Localization examples (based on READ)
<img src="docs/img/bottle_ad.png" width="50%" height="50%">
<img src="docs/img/metal_nut_ad.png" width="50%" height="50%">
<img src="docs/img/carpet_ad.png" width="50%" height="50%">
<img src="docs/img/hazelnut_ad.png" width="50%" height="50%">
<img src="docs/img/toothbrush_ad.png" width="50%" height="50%">

## Supported Algorithms
- [x] [RIAD](https://pdf.sciencedirectassets.com/272206/AIP/1-s2.0-S0031320320305094/main.pdf)
- [x] [FAVAE](https://arxiv.org/pdf/2008.05369.pdf)
- [x] [SPADE](https://arxiv.org/abs/2005.02357)
- [x] [PaDim](https://arxiv.org/pdf/2011.08785v1.pdf)
- [x] [USTAD](https://openaccess.thecvf.com/content_CVPR_2020/papers/Bergmann_Uninformed_Students_Student-Teacher_Anomaly_Detection_With_Discriminative_Latent_Embeddings_CVPR_2020_paper.pdf)
- [x] [STPM](https://arxiv.org/pdf/2103.04257v2.pdf)
- [x] [InTra](https://arxiv.org/pdf/2104.13897v2.pdf)
- [x] [SemiOrth](https://arxiv.org/pdf/2105.14737.pdf)

## Results
### Implementation results on MVTec
* Image-level anomaly detection accuracy (ROCAUC)

|MVTec|RIAD|FAVAE|SPADE-WR50X2|PaDiM-WR50X2|USTAD|STPM|SemiOrth-WR50X2|InTra|
|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
|Carpet|0.654|0.642|0.819|0.996|0.886|0.844|0.996|0.430|
|Grid|0.980|1.000|0.42|0.966|0.919|0.982|0.836|0.600|
|Leather|0.982|0.706|0.94|1.000|0.748|0.989|1.000|0.964|
|Tile|0.838|0.842|0.980|0.973|0.998|0.981|0.963|0.894|
|Wood|0.861|0.879|0.979|0.987|0.952|0.997|0.989|0.897|
|All texture classes|0.863|0.814|0.828|0.984|0.901|0.959|0.957|0.757|
|Bottle|0.984|0.999|0.972|0.999|0.940|1.000|0.995|0.947|
|Cable|0.543|0.942|0.857|0.880|0.478|0.874|0.779|0.562|
|Capsule|0.836|0.712|0.873|0.896|0.785|0.911|0.835|0.479|
|Hazelnut|0.904|0.999|0.907|0.950|0.939|0.986|0.973|0.776|
|Metal nut|0.820|0.911|0.734|0.987|0.509|0.988|0.917|0.466|
|Pill|0.789|0.779|0.785|0.935|0.798|0.982|0.744|0.554|
|Screw|0.746|0.595|0.658|0.846|0.706|0.871|0.470|0.665|
|Toothbrush|0.956|0.925|0.878|0.981|0.825|0.769|0.978|0.533|
|Transistor|0.890|0.885|0.900|0.983|0.563|0.810|0.927|0.520|
|Zipper|0.978|0.647|0.952|0.920|0.761|0.967|0.872|0.461|
|All object classes|0.845|0.839|0.852|0.9377|0.730|0.916|0.849|0.596|
|All classes|0.851|0.831|0.844|0.953|0.787|0.930|0.885|0.650|

* Pixel-level anomaly detection accuracy (ROCAUC)

|MVTec|RIAD|FAVAE|SPADE-WR50X2|PaDiM-WR50X2|USTAD|STPM|SemiOrth-WR50X2|InTra|
|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
|Carpet|0.904|0.836|0.985|0.988|0.958|0.977|0.989|0.468|
|Grid|0.984|0.994|0.978|0.969|0.850|0.983|0.860|0.631|
|Leather|0.990|0.908|0.993|0.991|0.914|0.991|0.993|0.989|
|Tile|0.761|0.626|0.942|0.940|0.948|0.969|0.935|0.873|
|Wood|0.821|0.908|0.956|0.946|0.899|0.940|0.950|0.715|
|All texture classes|0.892|0.854|0.971|0.967|0.914|0.972|0.945|0.735|
|Bottle|0.945|0.962|0.968|0.982|0.902|0.983|0.977|0.806|
|Cable|0.619|0.957|0.920|0.957|0.816|0.940|0.922|0.560|
|Capsule|0.978|0.965|0.983|0.985|0.913|0.973|0.981|0.774|
|Hazelnut|0.974|0.987|0.986|0.982|0.974|0.968|0.976|0.911|
|Metal nut|0.828|0.953|0.969|0.972|0.891|0.954|0.949|0.753|
|Pill|0.955|0.943|0.947|0.950|0.928|0.987|0.922|0.745|
|Screw|0.984|0.960|0.992|0.984|0.967|0.983|0.949|0.785|
|Toothbrush|0.966|0.984|0.989|0.988|0.947|0.982|0.989|0.692|
|Transistor|0.813|0.907|0.861|0.973|0.687|0.806|0.958|0.657|
|Zipper|0.981|0.817|0.982|0.983|0.825|0.987|0.975|0.497|
|All object classes|0.904|0.944|0.960|0.976|0.885|0.956|0.960|0.718|
|All classes|0.900|0.914|0.963|0.973|0.895|0.962|0.955|0.730|

## License
This project is released under the [Open-Intelligence Open Source License V1.1](LICENSE).

## 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.
<div align="left">
  <img src="docs/img/tcl_logo.jpg" width="200"/>
</div>
Any contributions to READ is welcome!