ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices https://arxiv.org/pdf/1707.01083.pdf
ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design https://arxiv.org/pdf/1807.11164.pdf
旷视科技提出新型轻量架构ShuffleNet V2
tensorflow 实现:https://github.com/TropComplique/shufflenet-v2-tensorflow
ShuffleNetV2:轻量级CNN网络中的桂冠
轻量级网络--ShuffleNet论文解读
Caffe实现:https://github.com/farmingyard/ShuffleNet
keras 实现:https://github.com/xiaohu2015/DeepLearning_tutorials/pulse
https://github.com/Randl/ShuffleNetV2-pytorch
https://github.com/miaow1988/ShuffleNet_V2_pytorch_caffe
https://github.com/ericsun99/Shufflenet-v2-Pytorch
https://github.com/timctho/shufflenet-v2-tensorflow
https://blog.csdn.net/huang_nansen/article/details/84075030
mobilenet https://blog.csdn.net/mzpmzk/article/details/82976871
ShuffleNet
大致对比一下 ShuffleNet v2 和 MobileNet v2 ,ShuffleNet v2只是多了快捷连接和 Channel shuffle
网友评论