Network Structure--dense and ResNet

Http://berwynzhang.com/2017/06/18/machine_learning/Inception-v4_Inception-ResNet_and_the_Impact_of_Residual_ connection_on_learning/***inception and Skip Connection

http://blog.csdn.net/quincuntial/article/details/77263607 ***resnet Translation

http://blog.csdn.net/buyi_shizi/article/details/53336192 *****resnet Understanding

http://blog.csdn.net/mao_feng/article/details/52734438

https://www.leiphone.com/news/201609/303vE8MIwFC7E3DB.html ****inceptionv4 + resnet

http://blog.csdn.net/Gavin__Zhou/article/details/53445539 ***resnet && densenet (principle)

https://data-sci.info/2017/07/26/%E6%AF%94resnet%E6%9B%B4%E5%8A%A0%E6%9C%89%E6%95%88%E7%9A%84%E7%B6%B2%E8%B7% af%e6%9e%b6%e6%a7%8b-densenet-densely-connected-convolutional-networks/***densenet

http://www.sohu.com/a/161639222_114877 ****dense Net

Https://baijia.baidu.com/s?id=1569620007658871&wfr=pc&fr=app_lst How to optimize large scale image classification neural network by evolutionary method.

HTTPS://BAIJIA.BAIDU.COM/S?ID=1587100594664128117&WFR=PC&FR=NEW_LST * * * * Google Cloud proposed progressive neural architecture search: Efficient search of high quality CNN structure

Notes on the implementation of Densenet in TensorFlow

https://medium.com/intuitionmachine/notes-on-the-implementation-densenet-in-tensorflow-beeda9dd1504

Network structure:

Http://www.cnblogs.com/52machinelearning/p/5821591.html

http://blog.csdn.net/xbinworld/article/details/45619685

Summarization of https://chenzomi12.github.io/2016/12/13/CNN-Architectures/*****cnn convolution neural network architecture

Inception depth Network Family Inventory | Inception V4 and inception-resnet the future direction?

http://nooverfit.com/wp/inception%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0%E5%AE%B6%E6%97%8F%E7%9B%98%E7%82% b9-inception-v4-%e5%92%8cinception-resnet%e6%9c%aa%e6%9d%a5%e8%b5%b0%e5%90%91%e4%bd%95%e6%96%b9/

http://blog.csdn.net/bea_tree/article/details/51865100 *****wide ResNet

http://blog.csdn.net/wspba/article/details/72229177

Http://blog.csdn.net/u014380165/article/details/78006893?reload ***msdnet 2018