# TorchGAN: A Flexible Framework for GAN Training and Evaluation

arXiv: https://arxiv.org/abs/1909.03410 · HTML: https://mlsanity.com/paper/1909.03410/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Sep 2019.

## Built on by (most cited first, 6 of 6)

- [TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systems](https://mlsanity.com/paper/2111.09999/) (2021)
- [medigan: a Python library of pretrained generative models for medical image synthesis](https://mlsanity.com/paper/2209.14472/) (2022)
- [On Characterizing GAN Convergence Through Proximal Duality Gap](https://mlsanity.com/paper/2105.04801/) (2021)
- [Seizing the Means of Production: Exploring the Landscape of Crafting, Adapting and Navigating Generative AI Models in the Visual Arts](https://mlsanity.com/paper/2404.17688/) (2024)
- [NSA: Naturalistic Support Artifact to Boost Network Confidence](https://mlsanity.com/paper/2307.14917/) (2023)
- [Deep learning as a tool for quantum error reduction in quantum image processing](https://mlsanity.com/paper/2311.04575/) (2023)

## Abstract (arXiv)

TorchGAN is a PyTorch based framework for writing succinct and comprehensible code for training and evaluation of Generative Adversarial Networks. The framework's modular design allows effortless customization of the model architecture, loss functions, training paradigms, and evaluation metrics. The key features of TorchGAN are its extensibility, built-in support for a large number of popular models, losses and evaluation metrics, and zero overhead compared to vanilla PyTorch. By using the framework to implement several popular GAN models, we demonstrate its extensibility and ease of use. We also benchmark the training time of our framework for said models against the corresponding baseline PyTorch implementations and observe that TorchGAN's features bear almost zero overhead.