The convolution kernel not only has height and width but also has depth
And it has the same depth as the feature map being convolved. Therefore, each convolution kernel can traverse all the feature maps of the upper level.
每一个卷积核遍历完所有的特征图之后，进行线性相加，就得到了新的特征图。 After each convolution kernel traverses all the feature maps, linear addition is performed to obtain a new feature map.
