Mixup

Implementation of the mixup training method

From hongyi-zhang·Updated March 5, 2026·View on GitHub·

This repo contains demo reimplementations of the CIFAR-10 training code and the GAN experiment in PyTorch based on the following paper: > Hongyi Zhang, Moustapha Cisse, Yann N. Dauphin and David Lopez-Paz. _mixup: Beyond Empirical Risk Minimization._ https://arxiv.org/abs/1710.09412 The project is written primarily in Python, distributed under the BSD 3-Clause "New" or "Revised" License license, first published in 2017. Key topics include: cifar, data-augmentation, gan, mixup, pytorch.

This repo contains demo reimplementations of the CIFAR-10 training code and the GAN experiment in PyTorch based on the following paper:

Hongyi Zhang, Moustapha Cisse, Yann N. Dauphin and David Lopez-Paz. mixup: Beyond Empirical Risk Minimization. https://arxiv.org/abs/1710.09412

CIFAR-10

The following table shows the median test errors of the last 10 epochs in a 200-epoch training session. (Please refer to Section 3.2 in the paper for details.)