artificial-intelligence - 卷积神经网络 - 如何获得特征图？

Question

我读了一些关于卷积神经网络的书籍和文章，似乎我理解了这个概念，但我不知道如何像下图那样把它表达出来：（ _{来源：what-when-how.com）}

从 28x28 归一化像素输入，我们得到 4 个大小为 24x24 的特征图。但如何得到它们？调整输入图像的大小？或执行图像转换？但是什么样的转变呢？或将输入图像切割成 4 块 24x24 x 4 角？我不明白这个过程，对我来说，他们似乎在每一步都将图像切割或调整为更小的图像。请帮忙谢谢。

Answer 1

这是 CONV2 函数的 matlab 帮助文件，在 CNN Matlab 中使用（获取卷积层）。仔细阅读，你会看到答案。

%CONV2 Two dimensional convolution.
%   C = CONV2(A, B) performs the 2-D convolution of matrices A and B.
%   If [ma,na] = size(A), [mb,nb] = size(B), and [mc,nc] = size(C), then
%   mc = max([ma+mb-1,ma,mb]) and nc = max([na+nb-1,na,nb]).
%
%   C = CONV2(H1, H2, A) convolves A first with the vector H1 along the
%   rows and then with the vector H2 along the columns. If n1 = length(H1)
%   and n2 = length(H2), then mc = max([ma+n1-1,ma,n1]) and 
%   nc = max([na+n2-1,na,n2]).
%
%   C = CONV2(..., SHAPE) returns a subsection of the 2-D
%   convolution with size specified by SHAPE:
%     'full'  - (default) returns the full 2-D convolution,
%     'same'  - returns the central part of the convolution
%               that is the same size as A.
%     'valid' - returns only those parts of the convolution
%               that are computed without the zero-padded edges.
%               **size(C) = max([ma-max(0,mb-1),na-max(0,nb-1)],0).**