All Projects → arunppsg → TadGAN

arunppsg / TadGAN

Licence: MIT License
Code for the paper "TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks"

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to TadGAN

progressive growing of GANs
Pure tensorflow implementation of progressive growing of GANs
Stars: ✭ 31 (-53.73%)
Mutual labels:  generative-adversarial-network, wasserstein-gan
skip-thought-gan
Generating Text through Adversarial Training(GAN) using Skip-Thought Vectors
Stars: ✭ 44 (-34.33%)
Mutual labels:  generative-adversarial-network, wasserstein-gan
Improved-Wasserstein-GAN-application-on-MRI-images
Improved Wasserstein GAN (WGAN-GP) application on medical (MRI) images
Stars: ✭ 23 (-65.67%)
Mutual labels:  generative-adversarial-network, wasserstein-gan
progressive-growing-of-gans.pytorch
Unofficial PyTorch implementation of "Progressive Growing of GANs for Improved Quality, Stability, and Variation".
Stars: ✭ 51 (-23.88%)
Mutual labels:  generative-adversarial-network, wasserstein-gan
wgan-gp
Pytorch implementation of Wasserstein GANs with Gradient Penalty
Stars: ✭ 161 (+140.3%)
Mutual labels:  wasserstein-gan, gradient-penalty
gan-qp.pytorch
Unofficial PyTorch implementation of "GAN-QP: A Novel GAN Framework without Gradient Vanishing and Lipschitz Constraint"
Stars: ✭ 26 (-61.19%)
Mutual labels:  generative-adversarial-network
keras-3dgan
Keras implementation of 3D Generative Adversarial Network.
Stars: ✭ 20 (-70.15%)
Mutual labels:  generative-adversarial-network
domain adapt
Domain adaptation networks for digit recognitioning
Stars: ✭ 14 (-79.1%)
Mutual labels:  generative-adversarial-network
gan-weightnorm-resnet
Generative Adversarial Network with Weight Normalization + ResNet
Stars: ✭ 19 (-71.64%)
Mutual labels:  generative-adversarial-network
RecycleGAN
The simplest implementation toward the idea of Re-cycle GAN
Stars: ✭ 68 (+1.49%)
Mutual labels:  generative-adversarial-network
private-data-generation
A toolbox for differentially private data generation
Stars: ✭ 80 (+19.4%)
Mutual labels:  generative-adversarial-network
TextBoxGAN
Generate text boxes from input words with a GAN.
Stars: ✭ 50 (-25.37%)
Mutual labels:  generative-adversarial-network
Deep-Learning
It contains the coursework and the practice I have done while learning Deep Learning.🚀 👨‍💻💥 🚩🌈
Stars: ✭ 21 (-68.66%)
Mutual labels:  generative-adversarial-network
ezgan
An extremely simple generative adversarial network, built with TensorFlow
Stars: ✭ 36 (-46.27%)
Mutual labels:  generative-adversarial-network
GAN-Ensemble-for-Anomaly-Detection
This repository is the PyTorch implementation of GAN Ensemble for Anomaly Detection.
Stars: ✭ 26 (-61.19%)
Mutual labels:  generative-adversarial-network
gans-collection.torch
Torch implementation of various types of GAN (e.g. DCGAN, ALI, Context-encoder, DiscoGAN, CycleGAN, EBGAN, LSGAN)
Stars: ✭ 53 (-20.9%)
Mutual labels:  generative-adversarial-network
MNIST-invert-color
Invert the color of MNIST images with PyTorch
Stars: ✭ 13 (-80.6%)
Mutual labels:  generative-adversarial-network
celeba-gan-pytorch
Generative Adversarial Networks in PyTorch
Stars: ✭ 35 (-47.76%)
Mutual labels:  generative-adversarial-network
tt-vae-gan
Timbre transfer with variational autoencoding and cycle-consistent adversarial networks. Able to transfer the timbre of an audio source to that of another.
Stars: ✭ 37 (-44.78%)
Mutual labels:  generative-adversarial-network
projects
things I help(ed) to build
Stars: ✭ 47 (-29.85%)
Mutual labels:  generative-adversarial-network

TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks

This is a Python3 / Pytorch implementation of TadGAN paper. The associated blog explaining the architecture details can be found here.

Data:

The TadGAN architecture can be used for detecting anomalies in time series data.

Pretrained Model:

The trained model is saved in the Model directory. The training is incomplete and the model has to be retrained for other datasets.

Architecture:

The model implements an encoder and decoder as generator and two critics as discriminators as described in the paper. The loss function is wasserstein loss with gradient penalty.

Usage:

  1. Format of the dataset - The dataset should have a column name as signal containing the signals and a column with name anomaly containing the true labels (used during validation).

  2. Delete the contents of the directory Model.

  3. Change the file name exchange-2_cpc_results.csv in main.py to the name of your dataset.

Note:

This is an independent implementation and I am not related to the authors of the paper.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].