samresume/SeriesGAN
We introduce an advanced framework that integrates the advantages of an autoencoder-generated embedding space with the adversarial training dynamics of GANs for time series generation.
This project helps data scientists and machine learning engineers create realistic synthetic time series data. It takes your existing time series datasets and generates new, high-fidelity time series that mimic the original patterns and distributions. This is useful for expanding datasets, testing models, or protecting privacy.
No commits in the last 6 months.
Use this if you need to generate new, synthetic time series data that accurately reflects your real-world observations.
Not ideal if you are looking for a tool to analyze or forecast existing time series data, as its primary purpose is generation.
Stars
10
Forks
2
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Oct 29, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/samresume/SeriesGAN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
PrasannaPulakurthi/MMD-AdversarialNAS-GAN
Enhancing GAN Performance Through Neural Architecture Search and Tensor Decomposition
aakashjhawar/AvatarGAN
Generate Cartoon Images using Generative Adversarial Network
nazmul-karim170/SPI-GAN
PyTorch Implementation of "SPI-GAN: Towards Single-Pixel Imaging through Generative Adversarial Network"
davide-abbattista/outGANfit
outGANfit - a cDCGANs-based architecture
abhi227070/Image-Generation-Using-GAN-Gen-AI-Project-
Gen AI uses GANs to generate CIFAR-10-like images. The custom GAN model comprises a Generator...