a Simple Development of CNN

a Simple Development of CNN

a simple development of CNN

networkfeature
LeNet-5foundation
AlexNet1.change the activation fun.;2.add dropout mechanism
GooleNet1.foundation:AlexNet;2.set up the inception Mechanism; 3.remove the full connected layer;4.begin to use 1x1 convolutional layer.
VGG1.foundation:AlexNet;2. remove local response normalization;3.big kernels are replaced by smaller one.
ResNet1.foundation:VGG;2.increase the number of layers;3.add shortcut connections to avoid degenerate

Actually my English is poor, I just want to use this way to improvement the level of my English.

I just forget the reference I have read, so I cannot give the reference here. Later if I can find any references I will add it to my blog.

And later I will also give the explation about some classical models.

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值