This article has not been completed, and is in the process of writing~
leave a draft here
Article directory
Overview
A convolutional neural network usually consists of 3 parts: 卷积层, 池化层, 全连接层. In short, the convolutional layer is responsible for extracting local and global features in the image; the pooling layer is used to greatly reduce the parameter magnitude (dimensionality reduction); the fully connected layer is used to process "compressed image information" and output the result .
1. Convolutional layer (CONV)
1. Basic properties of convolutional layers
The main function of the convolutional layer is to dynamically extract image features, which are composed of filters and activation functions. The general hyperparameters to be set include the number, size, step size of filters, type of activation function, and paddin