PyTorch GAN Zoo is a comprehensive open research toolbox designed for experimenting with and developing Generative Adversarial Networks (GANs) using PyTorch. The project provides modular implementations of popular GAN architectures, including Progressive Growing of GANs (PGAN), DCGAN, and an experimental StyleGAN version. It is built to support both researchers and developers who want to train, evaluate, and extend GANs efficiently across diverse datasets such as CelebA-HQ, FashionGen, DTD, and CIFAR-10. In addition to core GAN training, the repository includes tools for model evaluation, such as Inception Score and SWD metrics, as well as advanced features like GDPP for diverse generation and AC-GAN conditioning for class-specific synthesis. The framework also supports “inspirational generation,” enabling style or content transfer from reference images through pre-trained models.
Features
- Implements multiple GAN architectures including PGAN, DCGAN, and StyleGAN
- Supports advanced GAN methods such as GDPP loss and AC-GAN conditioning
- Includes evaluation metrics like SWD and Inception Score
- Provides pretrained checkpoints accessible via torch.hub
- Enables “inspirational generation” from reference images using feature extraction
- Compatible with popular image datasets including CelebA-HQ, FashionGen, and CIFAR-10
Project Samples
