shaohua0116/WGAN-GP-TensorFlow

TensorFlow implementations of Wasserstein GAN with Gradient Penalty (WGAN-GP), Least Squares GAN (LSGAN), GANs with the hinge loss.

38
/ 100
Emerging

This project helps machine learning researchers or practitioners generate realistic images from scratch after training a model on existing image datasets. You provide a collection of images (e.g., bedrooms, faces, or street scenes), and it produces new, diverse images that look like they belong to the same dataset. This is useful for tasks requiring synthetic data or creative image generation.

No commits in the last 6 months.

Use this if you need to generate high-quality, diverse synthetic images from a training dataset and want to leverage advanced Generative Adversarial Network (GAN) techniques for stable training.

Not ideal if you're not comfortable working with Python code and TensorFlow, or if your primary goal is image classification or object detection rather than image generation.

Image Generation Synthetic Data Computer Vision Research Generative AI Deep Learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

44

Forks

7

Language

Python

License

MIT

Last pushed

Jun 04, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/shaohua0116/WGAN-GP-TensorFlow"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.