community-events/huggan/pytorch/README.md

Example scripts (PyTorch)

This directory contains a few example scripts that allow you to train famous GANs on your own data using a bit of 🤗 magic.

More concretely, these scripts:

• leverage 🤗 Datasets to load any image dataset from the hub (including your own, possibly private, dataset)
• leverage 🤗 Accelerate to instantly run the script on (multi-) CPU, (multi-) GPU, TPU environments, supporting fp16 and mixed precision as well as DeepSpeed
• leverage 🤗 Hub to push the model to the hub at the end of training, allowing to easily create a demo for it afterwards

Currently, it contains the following examples:

Name	Paper
DCGAN	Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
pix2pix	Image-to-Image Translation with Conditional Adversarial Networks
CycleGAN	Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
Lightweight GAN	Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis