sjenni/dfgan
On Stabilizing Generative Adversarial Training with Noise. In CVPR, 2019.
This project helps researchers and machine learning practitioners explore advanced techniques for image generation. It takes a dataset of images, like CIFAR-10, and generates new, synthetic images that resemble the originals. Researchers in computer vision or AI who are studying or applying generative adversarial networks (GANs) would find this useful.
No commits in the last 6 months.
Use this if you are a computer vision researcher interested in applying or studying Generative Adversarial Networks (GANs) and want to experiment with methods to stabilize their training for better image generation.
Not ideal if you are looking for a plug-and-play solution for generating images without deep expertise in machine learning and Python, or if you require image generation for datasets other than CIFAR-10 without significant code modification.
Stars
7
Forks
5
Language
Python
License
MIT
Category
Last pushed
Feb 15, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/sjenni/dfgan"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
zhangqianhui/Conditional-GAN
Tensorflow implementation for Conditional Convolutional Adversarial Networks.
mit-han-lab/data-efficient-gans
[NeurIPS 2020] Differentiable Augmentation for Data-Efficient GAN Training
EugenHotaj/pytorch-generative
Easy generative modeling in PyTorch
kundan2510/pixelCNN
Theano reimplementation of pixelCNN architecture
shaohua0116/DCGAN-Tensorflow
A Tensorflow implementation of Deep Convolutional Generative Adversarial Networks trained on...