Git Product home page Git Product logo

yeonghyeon / memae Goto Github PK

View Code? Open in Web Editor NEW
7.0 3.0 3.0 1.43 MB

Implementation of Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection.

License: MIT License

Python 100.00%
mnist-dataset convolutional-neural-network convolutional-neural-networks anomaly-detection memorizing augmentation memory-augmentation deep-learning tensorflow tensorflow1

memae's Introduction

[TensorFlow] Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection

TensorFlow implementation of Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection. [PyTorch Version] [TensorFlow 2 Version]

Architecture

Architecture of MemAE.

Graph in TensorBoard

Graph of MemAE.

Problem Definition

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

Results

Restoration result by MemAE.

Box plot and histogram of restoration loss in test procedure.

Environment

  • Python 3.7.4
  • Tensorflow 1.14.0
  • Numpy 1.17.1
  • Matplotlib 3.1.1
  • Scikit Learn (sklearn) 0.21.3

Reference

[1] Dong Gong et al. (2019). Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection. arXiv preprint arXiv:1904.02639.

memae's People

Contributors

yeonghyeon avatar

Stargazers

avatar avatar avatar avatar avatar avatar avatar

Watchers

avatar avatar avatar

Forkers

saikumarkethi kuanliang ggn1

memae's Issues

MSE is not stable, and jumb much

see these samples,
the MSE in the new epoch is very large than the old one,
I thought this might be the Learning rate, but the lr is 1e-4

Do you have an idea how to handle this problem?

Epoch [2281 / 10000] (59332 iteration) MSE:383912.281, W-ETRP:0.003, Total:7678.246

Epoch [2285 / 10000] (59436 iteration) MSE:198418.922, W-ETRP:0.003, Total:3968.378

Epoch [2308 / 10000] (60034 iteration) MSE:327438.281, W-ETRP:0.003, Total:6548.765

Epoch [2313 / 10000] (60164 iteration) MSE:308482.469, W-ETRP:0.003, Total:6169.649

[2315 / 10000] (60216 iteration) MSE:152412.391, W-ETRP:0.003, Total:3048.248

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.