mit-han-lab/data-efficient-gans
MIT research project implementing Differentiable Augmentation to enable GAN training with as few as 100 images through learned data transformations.
Not currently ranked — collecting fresh signals.
star history
This repository provides a research implementation of Differentiable Augmentation (DiffAugment) for training Generative Adversarial Networks more efficiently with limited data. It includes PyTorch and TensorFlow implementations supporting StyleGAN2 and BigGAN architectures. The technique applies differentiable augmentation during training to stabilize GAN learning when only small datasets are available, enabling high-quality image generation from as few as 100 training examples without pre-training.
Frequently asked
- What is mit-han-lab/data-efficient-gans?
- MIT research project implementing Differentiable Augmentation to enable GAN training with as few as 100 images through learned data transformations.
- Is data-efficient-gans open source?
- Yes — mit-han-lab/data-efficient-gans is open source, released under the BSD-2-Clause license.
- What language is data-efficient-gans written in?
- mit-han-lab/data-efficient-gans is primarily written in Python.
- How popular is data-efficient-gans?
- mit-han-lab/data-efficient-gans has 1.3k stars on GitHub.
- Where can I find data-efficient-gans?
- mit-han-lab/data-efficient-gans is on GitHub at https://github.com/mit-han-lab/data-efficient-gans.