Mimicry Documentation

Mimicry is a lightweight PyTorch library aimed towards the reproducibility of GAN research.

Comparing GANs is often difficult - mild differences in implementations and evaluation methodologies can result in huge performance differences. Mimicry aims to resolve this by providing:

• Standardized implementations of popular GANs that closely reproduce reported scores
• Baseline scores of GANs trained and evaluated under the same conditions
• A framework for researchers to focus on implementation of GANs without rewriting most of GAN training boilerplate code, with support for multiple GAN evaluation metrics.

Guides

• Introduction
• Tutorial
• Baselines

API Reference

• torch_mimicry.nets
• torch_mimicry.modules
• torch_mimicry.training
• torch_mimicry.metrics
• torch_mimicry.datasets
• torch_mimicry.utils