birdx0810/timegan-pytorch
This repository is a non-official implementation of TimeGAN (Yoon et al., NIPS2019) using PyTorch.
This project helps data scientists and researchers create realistic synthetic time-series data when they have limited real data or need to protect privacy. It takes existing time-series datasets, like stock prices, and generates new, artificial time-series sequences that mimic the statistical properties and patterns of the original data. This is useful for training machine learning models or testing algorithms without exposing sensitive real-world information.
No commits in the last 6 months.
Use this if you need to generate artificial time-series data that closely resembles your real data for model training, privacy preservation, or data augmentation.
Not ideal if you require an exact reproduction of the original TimeGAN paper's experimental results or if you need a solution without known issues that may impact accuracy.
Stars
84
Forks
38
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jul 26, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/birdx0810/timegan-pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
huggingface/pytorch-pretrained-BigGAN
🦋A PyTorch implementation of BigGAN with pretrained weights and conversion scripts.
torchgan/torchgan
Research Framework for easy and efficient training of GANs based on Pytorch
metal3d/keras-video-generators
Keras generators to generate sequences from videos as input
GANs-in-Action/gans-in-action
Companion repository to GANs in Action: Deep learning with Generative Adversarial Networks
junyanz/pytorch-CycleGAN-and-pix2pix
Image-to-Image Translation in PyTorch