vandit15/Self-Supervised-Gans-Pytorch

Ready to train Pytorch implementation of the CVPR'19 paper "Self-Supervised GANs via Auxiliary Rotation Loss"

43
/ 100
Emerging

This project helps machine learning engineers and researchers generate realistic synthetic images, even with limited labeled data. By combining adversarial training with a self-supervised task of predicting image rotations, it produces higher quality images and more robust feature representations. The user provides a dataset of images, and the system outputs a trained generative model capable of creating new, diverse images that resemble the training data.

No commits in the last 6 months.

Use this if you need to generate high-quality synthetic images and want to improve the stability and performance of your Generative Adversarial Networks (GANs), especially when dealing with smaller datasets.

Not ideal if your primary goal is not image generation, or if you require a solution that does not involve deep learning frameworks like PyTorch.

synthetic-data-generation image-synthesis generative-modeling unsupervised-learning deep-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

66

Forks

18

Language

Python

License

MIT

Last pushed

Nov 12, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/vandit15/Self-Supervised-Gans-Pytorch"

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