版权声明：本文为博主原创文章，未经博主允许不得转载。					https://blog.csdn.net/qq_15933615/article/details/79828225				</div>
							<link rel="stylesheet" href="https://csdnimg.cn/release/phoenix/template/css/ck_htmledit_views-f57960eb32.css">
							            <div id="content_views" class="markdown_views prism-atom-one-dark">
						<!-- flowchart 箭头图标 勿删 -->
						<svg xmlns="http://www.w3.org/2000/svg" style="display: none;"><path stroke-linecap="round" d="M5,0 0,2.5 5,5z" id="raphael-marker-block" style="-webkit-tap-highlight-color: rgba(0, 0, 0, 0);"></path></svg>
						<h1 id="1lenet-5"><a name="t0"></a>1.LeNet-5</h1>

论文《Gradient-based learning applied to document recognition》
web：http://yann.lecun.com/exdb/lenet/

2.AlexNet

论文《ImageNet Classification with Deep Convolutional Neural Networks》

3.ZFNet

论文《Visualizing and Understanding Convolutional Networks》
arxiv：https://arxiv.org/abs/1311.2901

4.Network In Network

论文《Network In Network》

5.VGG

论文《Very Deep Convolutional Networks for Large-Scale Image Recognition》
web：http://www.robots.ox.ac.uk/~vgg/research/very_deep/
slides：http://www.robots.ox.ac.uk/~karen/pdf/ILSVRC_2014.pdf

6.GoogLeNet(Inception V1)

论文《Going Deeper with Convolutions》
arxiv：https://arxiv.org/abs/1409.4842

7.Inception V2

论文《Batch Normalization：Accelerating Deep Network Training by Reducing Internal Covariate Shift》

8.Inception V3

论文《Rethinking the Inception Architecture for Computer Vision》
arxiv：https://arxiv.org/abs/1512.00567

一个5×5的卷积核可以由2次3×3的卷积代替

一个3×3的卷积核可以由1×3和3×1的卷积代替

原始Inception结构

把5×5的卷积由2次3×3的卷积代替后的Inception结构

把n×n的卷积由1×n和n×1的卷积代替后的Inception结构

9.Inception V4，Inception-ResNet

论文《Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning》
arxiv：https://arxiv.org/abs/1602.07261

Inception-v4

Stem

Inception-A

Reduction-A

Inception-B

Reduction-B

Inception-C

Inception-ResNet-v1

Inception-ResNet-v2

10.ResNet

论文《Deep Residual Learning for Image Recognition》
arxiv：https://arxiv.org/abs/1512.03385

11.SqueezeNet

论文《SqueezeNet：AlexNet-level accuracy with 50x fewer parameters and 0.5MB model size》

12.DenseNet

论文《Densely Connected Convolutional Networks》
arxiv：https://arxiv.org/abs/1608.06993

13.Xception

论文《Xception: Deep Learning with Depthwise Separable Convolutions》
arxiv：https://arxiv.org/abs/1610.02357

14.ResNeXt

论文《Aggregated Residual Transformations for Deep Neural Networks》
arxiv：https://arxiv.org/abs/1611.05431

15.PolyNet

论文《PolyNet: A Pursuit of Structural Diversity in Very Deep Networks》
arxiv：https://arxiv.org/abs/1611.05431

16.MobileNet

论文《MobileNets：Efficient Convolutional Neural Networks for Mobile Vision Applications》

17.ShuffleNet

论文《ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices》

18.DPN

论文《Dual Path Networks》
arxiv：https://arxiv.org/abs/1707.01629

19.NASNet

论文《Learning transferable architectures for scalable image recognition》

20.SENet

论文《Squeeze-and-Excitation Networks》

21.MobileNet v2

论文《Inverted Residuals and Linear Bottlenecks：Mobile Networks for Classification, Detection and Segmentation》