Download
compare_gan is a research codebase that standardizes how Generative Adversarial Networks are trained and evaluated so results are comparable across papers and datasets. It offers reference implementations for popular GAN architectures and losses, plus a consistent training harness to remove confounding differences in optimization or preprocessing. The library’s evaluation suite includes widely used metrics and diagnostics that quantify sample quality, diversity, and mode coverage. With configuration-driven experiments, you can sweep hyperparameters, run ablations, and log results at scale. The goal is to turn GAN experimentation into a disciplined, repeatable process rather than a patchwork of scripts. It also provides baselines strong enough to serve as starting points for new ideas without re-implementing the world.
Features
- Reference implementations of common GAN architectures and losses
- Unified training loop with consistent optimization and preprocessing
- Metrics for quality, diversity, and mode coverage
- Config-driven experiments for sweeps and ablations
- Reproducible logging, checkpoints, and result tracking
- Strong baselines to accelerate new GAN research
Project Samples
