https://github.com/yeonghyeon/memae-tf2
TensorFlow implementation of "Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection"
https://github.com/yeonghyeon/memae-tf2
anomaly-detection augmentation convolutional-neural-network convolutional-neural-networks deep-learning memorizing memory-augmentation mnist-dataset tensorflow tensorflow2
Last synced: 7 months ago
JSON representation
TensorFlow implementation of "Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection"
- Host: GitHub
- URL: https://github.com/yeonghyeon/memae-tf2
- Owner: YeongHyeon
- License: mit
- Created: 2020-02-20T14:01:59.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2023-06-11T07:00:37.000Z (about 3 years ago)
- Last Synced: 2025-04-26T17:47:12.791Z (about 1 year ago)
- Topics: anomaly-detection, augmentation, convolutional-neural-network, convolutional-neural-networks, deep-learning, memorizing, memory-augmentation, mnist-dataset, tensorflow, tensorflow2
- Language: Python
- Homepage:
- Size: 736 KB
- Stars: 25
- Watchers: 2
- Forks: 5
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
[TensorFlow 2] 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 1 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 2.1.0
* Numpy 1.18.1
* Matplotlib 3.1.3
* Scikit Learn (sklearn) 0.22.1
## 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.