Home

Awesome

ChannelNets

Created by Hongyang Gao, Zhengyang Wang, and Shuiwang Ji at Texas A&M University.

Introduction

ChannelNets are compact and efficent CNN via Channel-wise convolutions. It has been accepted in NIPS2018.

Detailed information about ChannelNets is provided in https://papers.nips.cc/paper/7766-channelnets-compact-and-efficient-convolutional-neural-networks-via-channel-wise-convolutions.pdf.

Citation

@inproceedings{gao2018channelnets,
  title={ChannelNets: Compact and Efficient Convolutional Neural Networks via Channel-Wise Convolutions},
  author={Gao, Hongyang and Wang, Zhengyang and Ji, Shuiwang},
  booktitle={Advances in Neural Information Processing Systems},
  pages={5203--5211},
  year={2018}
}

Results

ModelsTop-1ParamsFLOPs
GoogleNet0.6986.8m1550m
VGG160.715128m15300m
AlexNet0.57260m720m
SqueezeNet0.5751.3m833m
1.0 MobileNet0.7064.2m569m
ShuffleNet 2x0.7095.3m524m
ChannelNet-v10.7053.7m407m

Configure the network

All network hyperparameters are configured in main.py.