angeluriot/Generative_adversarial_network

A deep learning model that can create high quality images by training on a dataset.

24
/ 100
Experimental

Implements a style-based architecture combining equalized learning rates, wavelet transforms, and adaptive discriminator augmentation across both generator and discriminator networks. Built on PyTorch with training stability features including path length regularization, gradient penalty, and Fréchet Inception Distance (FID) evaluation. Supports multi-dataset training with checkpoint resumption and includes latent space projection, style mixing, and interpolation capabilities for advanced image synthesis control.

No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

52

Forks

Language

Python

License

MIT

Last pushed

Jan 14, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/angeluriot/Generative_adversarial_network"

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