92.45% on CIFAR-10 in Torch
Lua
Latest commit 704d431 Oct 19, 2016 @fredowski fredowski committed with added cudnn.benchmark=true to speedup gpu computations (#22)
I tested this on a GTX1080. The steptime improved from 220 ms
to 50 ms.

README.md

cifar.torch

Newer version of this code is included in https://github.com/szagoruyko/wide-residual-networks

The code achieves 92.45% accuracy on CIFAR-10 just with horizontal reflections.

Corresponding blog post: http://torch.ch/blog/2015/07/30/cifar.html

Accuracies:

No flips Flips
VGG+BN+Dropout 91.3% 92.45%
NIN+BN+Dropout 90.4% 91.9%

Would be nice to add other architectures, PRs are welcome!

Data preprocessing:

OMP_NUM_THREADS=2 th -i provider.lua
provider = Provider()
provider:normalize()
torch.save('provider.t7',provider)

Takes about 30 seconds and saves 1400 Mb file.

Training:

CUDA_VISIBLE_DEVICES=0 th train.lua --model vgg_bn_drop -s logs/vgg