Dimensional changes after CNN convolutional pooling

Dimensional changes after CNN's convolution operation:

1. Input dimensions:, respectively represent the length, width and height of the input sample
2. Hyperparameters of convolution operation
   1. Number of convolution kernels:
   2. Convolution kernel size:
   3. Stride:
   4. Padding:
3. The output dimension is , where
   1. 
   2. 
   3. 
4. Due to the parameter sharing mechanism of CNN, the number of parameters of each convolution kernel is , there are a total of weights and biases
5. If you want to be consistent after convolution with a convolution matrix length and width before, when the time
   1. When the convolution kernel is 3, padding select 1
   2. When the convolution kernel is 5, padding select 2
   3. When the convolution kernel is 7, padding chooses 3

Dimension changes after CNN's pooling operation:

1. Input dimensions:, respectively represent the length, width and height of the input sample
2. Hyperparameters for pooling operations
   1. Pooling layer size:
   2. Stride:
   3. Padding:
3. The output dimension is , where
   1. 
   2. 
   3. 

Reference materials: https://blog.csdn.net/qq_41670192/article/details/79231732