3-3 Convolutional Neural Network

Why should a non-linear function be used as an activation function?

The default step size of convolution is 1, and the default step size of pooling is the same as the size of kernel_size

After the fully connected layer, the convolutional layer and the pooling layer cannot be added

 

 

Guess you like

Origin blog.csdn.net/weixin_43135178/article/details/113240126