rish-16/TransGAN-PyTorch
[WIP] PyTorch implementation of the TransGAN paper
This is a PyTorch implementation of TransGAN. It helps deep learning researchers and practitioners experiment with generating realistic images from random noise, leveraging the architecture proposed in the original TransGAN paper. You provide random input data, and it outputs newly synthesized images.
No commits in the last 6 months.
Use this if you are a deep learning researcher or practitioner interested in exploring or applying Generative Adversarial Networks (GANs) that incorporate Transformer architectures for image generation tasks.
Not ideal if you are looking for a plug-and-play solution for general image generation without deep learning expertise, or if you need to generate other data types beyond images.
Stars
13
Forks
5
Language
Python
License
MIT
Category
Last pushed
Feb 26, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/rish-16/TransGAN-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