openai/improved-gan
An OpenAI research implementation of techniques for training Generative Adversarial Networks on image generation tasks.
Not currently ranked — collecting fresh signals.
star history
This repository contains the official code for the 2016 paper ‘Improved Techniques for Training GANs’ by Salimans et al. It provides implementations for training GANs on standard benchmarks including MNIST, SVHN, CIFAR-10, and ImageNet. The code includes experimental setups for semi-supervised learning and techniques to stabilize GAN training.
Frequently asked
- What is openai/improved-gan?
- An OpenAI research implementation of techniques for training Generative Adversarial Networks on image generation tasks.
- Is improved-gan open source?
- Yes — openai/improved-gan is an open-source project tracked on heatdrop.
- What language is improved-gan written in?
- openai/improved-gan is primarily written in Python.
- How popular is improved-gan?
- openai/improved-gan has 2.3k stars on GitHub.
- Where can I find improved-gan?
- openai/improved-gan is on GitHub at https://github.com/openai/improved-gan.