Code for CIFAR-10 competition. http://www.kaggle.com/c/cifar-10
Description | |
---|---|
Model | Very Deep Convolutional Networks with 3x3 kernel [1] |
Data Augmentation | cropping, horizontal reflection [2] and scaling. see lib/data_augmentation.lua |
Preprocessing | Global Contrast Normalization (GCN) and ZCA whitening. see lib/preprocessing.lua |
Training Time | 20 hours on GTX760. |
Prediction Time | 2.5 hours on GTX760. |
Result | 0.93320 (single model). 0.94150 (average 6 models) |
Layer type | Parameters |
---|---|
input | size: 24x24, channel: 3 |
convolution | kernel: 3x3, channel: 64, padding: 1 |
relu | |
convolution | kernel: 3x3, channel: 64, padding: 1 |
relu | |
max pooling | kernel: 2x2, stride: 2 |
dropout | rate: 0.25 |
convolution | kernel: 3x3, channel: 128, padding: 1 |
relu | |
convolution | kernel: 3x3, channel: 128, padding: 1 |
relu | |
max pooling | kernel: 2x2, stride: 2 |
dropout | rate: 0.25 |
convolution | kernel: 3x3, channel: 256, padding: 1 |
relu | |
convolution | kernel: 3x3, channel: 256, padding: 1 |
relu | |
convolution | kernel: 3x3, channel: 256, padding: 1 |
relu | |
convolution | kernel: 3x3, channel: 256, padding: 1 |
relu | |
max pooling | kernel: 2x2, stride: 2 |
dropout | rate: 0.25 |
linear | channel: 1024 |
relu | |
dropout | rate: 0.5 |
linear | channel: 1024 |
relu | |
dropout | rate: 0.5 |
linear | channel: 10 |
softmax |
- Ubuntu 14.04
- 15GB RAM (This codebase can run on g2.2xlarge!)
- CUDA (GTX760 or more higher GPU)
- Torch7 latest
- cuda-convnet2.torch
(This document is outdated. See: Getting started with Torch)
Install CUDA (on Ubuntu 14.04):
apt-get install nvidia-331
apt-get install nvidia-cuda-toolkit
Install Torch7 (see Torch (easy) install):
curl -s https://raw.githubusercontent.com/torch/ezinstall/master/install-all | bash
Install(or upgrade) dependency packages:
luarocks install torch
luarocks install nn
luarocks install cutorch
luarocks install cunn
luarocks install https://raw.githubusercontent.com/soumith/cuda-convnet2.torch/master/ccn2-scm-1.rockspec
th cuda_test.lua
Please check your Torch7/CUDA environment when this code fails.
Place the data files into a subfolder ./data.
ls ./data
test train trainLabels.csv
- th convert_data.lua
th validate.lua
dataset:
train | test |
---|---|
1-40000 | 40001-50000 |
th train.lua
th predict.lua