2.56% Test Error on CIFAR-10 using PyTorch and AutoAugment

Top-tier conferences in machine learning or computer vision generally require state-of-the-art results as baseline to assess novelty and significance of the paper. Unfortunately, getting state-of-the-art results on many benchmarks can be tricky and extremely time-consuming — even for rather simple benchmarks such as CIFAR-10. In this article, I want to share PyTorch code for obtaining 2.56% test error on CIFAR-10 using a Wide ResNet (WRN-28-10) and AutoAugment as well as Cutout for data augmentation.

The post 2.56% Test Error on …

art article augmentation benchmarks blog cifar-10 code computer computer vision conferences data david deep learning error machine machine learning paper python pytorch resnet significance state test vision