适合移动端的轻量级网络

MobileNet

【MobileNet v1】https://arxiv.org/pdf/1704.04861.pdf
【MobileNet v2】https://arxiv.org/pdf/1801.04381.pdf
深度解读谷歌MobileNet
深度可分离卷积(depthwise separable convolution)参数计算

关键在于1x1卷积减少了参数量和计算量
轻量化网络:MobileNet-V2

我的模型有多快?——深度学习网络模型的运算复杂度、空间占用和内存访问情况计算

MobileNet 结构简单微调的一点性能提升

ShuffleNet

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

SqueezeNet:

https://blog.csdn.net/williamyi96/article/details/77604356
【论文】https://arxiv.org/pdf/1602.07360.pdf

NasNet:

https://blog.csdn.net/xjz18298268521/article/details/79079008
【论文】https://arxiv.org/pdf/1707.07012.pdf

MNasNet:

【荐】学界 | MnasNet论文解读:终端轻量化模型新思路
【论文】https://arxiv.org/pdf/1807.11626.pdf
https://blog.csdn.net/lsy17096535/article/details/82878963

你可能感兴趣的:(适合移动端的轻量级网络)