@article{He2015,
    author = {Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun},
    title = {Deep Residual Learning for Image Recognition},
    journal = {arXiv preprint arXiv:1512.03385},
    year = {2015}
	}

This repository reimplements resnet experiments on cifar10 with caffe according to the paper "Deep Residual Learning for Image Recognition" (http://arxiv.org/abs/1512.03385). The data augmentation means 4 pixels are padded on each side for every images during training. You can make datasets prepared by using the scripts.

The network structure is here(we only list the network of 20 depth):
ResNet_20
PlainNet_20

First, you should make sure that your caffe is correctly installed. You can follow this blog's instructions if you use windows.(https://zhuanlan.zhihu.com/p/22129880)

for training

caffe train -solver=solver.prototxt -gpu 0

for testing

caffe test -model=res20_cifar_train_test.prototxt -weights=ResNet_20.caffemodel -iterations=100 -gpu 0

notice:'Repeated' means reimplementation results and 'Reference' means result in the paper.We got even better results than the original paper

zhihu