Home

Awesome

A PyTorch implementation of RICAP

This repository contains code for a data augmentation method RICAP (Random Image Cropping And Patching) based on Data Augmentation using Random Image Cropping and Patching for Deep CNNs implemented in PyTorch.

example

Requirements

Training

CIFAR-10

WideResNet28-10 baseline on CIFAR-10:

python train.py --dataset cifar10

WideResNet28-10 +RICAP on CIFAR-10:

python train.py --dataset cifar10 --ricap True

WideResNet28-10 +Random Erasing on CIFAR-10:

python train.py --dataset cifar10 --random-erase True

WideResNet28-10 +Mixup on CIFAR-10:

python train.py --dataset cifar10 --mixup True

Results

ModelError rateLossError rate (paper)
WideResNet28-10 baseline3.820.1583.89
WideResNet28-10 +RICAP2.820.1412.85
WideResNet28-10 +Random Erasing3.180.1144.65
WideResNet28-10 +Mixup3.020.1583.02

Learning curves of loss and accuracy.

loss

acc