https://github.com/yeonghyeon/cvae-anomalydetection-pytorch

Example of Anomaly Detection using Convolutional Variational Auto-Encoder (CVAE)
https://github.com/yeonghyeon/cvae-anomalydetection-pytorch

anomaly-detection convolutional-neural-networks generative-neural-network mnist-dataset pytorch variational-autoencoder

Last synced: 5 days ago
JSON representation

Example of Anomaly Detection using Convolutional Variational Auto-Encoder (CVAE)

• Host: GitHub
• URL: https://github.com/yeonghyeon/cvae-anomalydetection-pytorch
• Owner: YeongHyeon
• Created: 2019-11-07T10:32:01.000Z (about 5 years ago)
• Default Branch: master
• Last Pushed: 2024-04-09T17:38:24.000Z (7 months ago)
• Last Synced: 2024-04-09T19:36:13.729Z (7 months ago)
• Topics: anomaly-detection, convolutional-neural-networks, generative-neural-network, mnist-dataset, pytorch, variational-autoencoder
• Language: Python
• Homepage:
• Size: 2.31 MB
• Stars: 36
• Watchers: 5
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
[PyTorch] Anomaly Detection using Convolutional Variational Auto-Encoder (CVAE)

=====

Example of Anomaly Detection using Convolutional Variational Auto-Encoder (CVAE) [TensorFlow 1.x] [TensorFlow 2.x].

## Architecture



    

  
Simplified VAE architecture.



## Problem Definition



    

  
'Class-1' is defined as normal and the others are defined as abnormal.



## Results

||MNIST|Fashion-MNIST|

|:---|:---:|:---:|

|Reconstruciton of training|||

|Latent of training|||

|Latent walk|||

|Latent of test|||

|Histogram of test|||

|AUROC|0.997|0.980|

## Environment

* Python 3.7.4  

* PyTorch 1.1.0   

* Numpy 1.17.1  

* Matplotlib 3.1.1  

* Scikit Learn (sklearn) 0.21.3  

## Reference

[1] Kingma, D. P., & Welling, M. (2013). Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114.  

[2] Kullback Leibler divergence. Wikipedia