Awesome

Parallel Grid Pooling for Data Augmentation

This repository contains the code for the paper Parallel Grid Pooling for Data Augmentation.

Requirements

• Python 3.5+
• Chainer 5.0.0b4+
• CuPy 5.0.0b4+
• ChainerCV 0.10.0+
• ChainerMN 1.3.0+

Training

To train PreResNet-164 on CIFAR-10 dataset with single-GPU:

$ python train.py --dataset cifar10 --model PreResNet164 --gpus 0

To train ResNet-50 on ImageNet dataset with multi-GPU:

$ python train_imagenet.py --model ResNet50_fb --gpus 0,1,2,3,4,5,6,7

Results on CIFAR-10

Test errors (%)

Weight Transfer

Test errors (%) (Test-time data augmentation)

Test errors (%) (Training-time data augmentation)

Results on ImageNet and Pretrained Models

The error rates (%) shown are 224x224 1-crop test errors.

Citation

@article{Takeki18Parallel,
    title = {Parallel Grid Pooling for Data Augmentation},
    author = {Takeki, Akito and Ikami, Daiki and Irie, Go and Aizawa, Kiyoharu},
    journal = {arXiv preprint arXiv:1803.11370},
    year = 2018,
}