Awesome
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.)
| Model | weight decay = 1e-4 | weight decay = 5e-4 |
|---|---|---|
| ERM | 5.53% | 5.18% |
| mixup | 4.24% | 4.68% |
Generative Adversarial Networks (GAN)
Other implementations
- A Tensorflow implementation of mixup which reproduces our results in tensorpack
- Official Facebook implementation of the CIFAR-10 experiments
Acknowledgement
The CIFAR-10 reimplementation of mixup is adapted from the pytorch-cifar repository by kuangliu.