vandit15/Self-Supervised-Gans-Pytorch
Ready to train Pytorch implementation of the CVPR'19 paper "Self-Supervised GANs via Auxiliary Rotation Loss"
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.
Stars
66
Forks
18
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
yunjey/domain-transfer-network
TensorFlow Implementation of Unsupervised Cross-Domain Image Generation
taesungp/contrastive-unpaired-translation
Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV...
PaddlePaddle/PaddleGAN
PaddlePaddle GAN library, including lots of interesting applications like First-Order motion...
tohinz/ConSinGAN
PyTorch implementation of "Improved Techniques for Training Single-Image GANs" (WACV-21)
sagiebenaim/DistanceGAN
Pytorch implementation of "One-Sided Unsupervised Domain Mapping" NIPS 2017