The basic composition of neural networks includes input layer, hidden layer, and
output layer. The characteristic of the convolutional neural network is that the hidden layer is divided into a convolutional layer and a pooling layer
(also called a downsampling layer ).
• **Convolutional layer: **Features are extracted by translation on the original image. Each feature
is a feature map.
• Pooling layer : Reduce the learned parameters and reduce
the complexity of the network through sparse parameters after the feature. Pooling and average pooling)
h1=99.5, take 99. Because the step size is 2, zeros are filled with 1. The last 0.5 represents 1 step, which is zero padding. All 0.5 can be omitted,