EndlessSora/DeceiveD
[NeurIPS 2021] Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data
This project helps artists, designers, or researchers who need to create realistic or stylized images but have only a small number of example images available. You provide a limited collection of images, and it outputs a generator that can produce a vast array of new, diverse, and high-quality images that look consistent with your input examples. This is perfect for those who work with niche visual content or rare datasets.
235 stars. No commits in the last 6 months.
Use this if you need to generate high-quality, realistic images using Generative Adversarial Networks (GANs) but are severely limited by the amount of training data you possess.
Not ideal if you already have a very large and diverse dataset for training your image generation models.
Stars
235
Forks
24
Language
Python
License
—
Category
Last pushed
Dec 09, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/EndlessSora/DeceiveD"
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...