LeNet-5 ,以用于实现手写识别的7层CNN(不包含输入层)为例,以下为LeNet-5的示意图:
![](https://i-blog.csdnimg.cn/blog_migrate/7f53d2feb70860918dbf3b854baefdef.png)
Input Layer:1*32*32图像
Conv1 Layer:包含6个卷积核,kernal size:5*5,parameters:(5*5+1)*6=156个
Subsampling Layer:average pooling,size:2*2
Activation Function:sigmoid
Conv3 Layer:包含16个卷积核,kernal size:5*5 ->16个Feature Map
Subsampling Layer:average pooling,size:2*2
Conv5 Layer:包含120个卷积核,kernal size:5*5
Fully Connected Layer:Activation Function:sigmoid
Output Layer:Gaussian connections