给定一个矩阵 A ( mxnxc )( c 可以是任意的),我想对补丁进行采样( pxp )在滑动窗口方案中使用stepsize d ,并将所有 pxpxc 补丁重新排列到矢量中。 我可以在嵌套的for循环中完成它,但它非常耗时。如何快速完成?
答案 0 :(得分:4)
可以使用this solution to Efficient Implementation of im2col and col2im
再次展开bsxfun
以获取3D数组大小写以解决您的问题。
现在,对这个问题有两种可能的解释:
提取大小为2D
的块和每个向量,为整个第一个3D
切片执行此操作,然后对3D
中的所有切片重复此操作,生成{{ 1}}输出。
将每个大小为p x p x c
的块作为向量集合,并以滑动的方式在整个数组中执行此操作,从而产生2D
输出。
这两种解释分别实现为im2col_3D_sliding_v1
和im2col_3D_sliding_v2
,然后列出。
im2col_3D_sliding_v1:
function out = im2col_3D_sliding_v1(A,blocksize,stepsize)
%// Store blocksizes
nrows = blocksize(1);
ncols = blocksize(2);
%// Store stepsizes along rows and cols
d_row = stepsize(1);
d_col = stepsize(2);
%// Get sizes for later usages
[m,n,r] = size(A);
%// Start indices for each block
start_ind = reshape(bsxfun(@plus,[1:d_row:m-nrows+1]',[0:d_col:n-ncols]*m),[],1); %//'
%// Row indices
lin_row = permute(bsxfun(@plus,start_ind,[0:nrows-1])',[1 3 2]); %//'
%// 2D linear indices
lidx_2D = reshape(bsxfun(@plus,lin_row,[0:ncols-1]*m),nrows*ncols,[]);
%// 3D linear indices
lidx_3D = bsxfun(@plus,lidx_2D,m*n*permute((0:r-1),[1 3 2]));
%// Get linear indices based on row and col indices and get desired output
out = A(lidx_3D);
return;
im2col_3D_sliding_v2:
function out = im2col_3D_sliding_v2(A,blocksize,stepsize)
%// Store blocksizes
nrows = blocksize(1);
ncols = blocksize(2);
%// Store stepsizes along rows and cols
d_row = stepsize(1);
d_col = stepsize(2);
%// Get sizes for later usages
[m,n,r] = size(A);
%// Start indices for each block
start_ind = reshape(bsxfun(@plus,[1:d_row:m-nrows+1]',[0:d_col:n-ncols]*m),[],1); %//'
%// Row indices
lin_row = permute(bsxfun(@plus,start_ind,[0:nrows-1])',[1 3 2]); %//'
%// 2D linear indices
lidx_2D = reshape(bsxfun(@plus,lin_row,[0:ncols-1]*m),nrows*ncols,[]);
%// 3D linear indices
lidx_3D = bsxfun(@plus,permute(lidx_2D,[1 3 2]),m*n*(0:r-1));
%// Final 2D linear indices
lidx_2D_final = reshape(lidx_3D,[],size(lidx_2D,2));
%// Get linear indices based on row and col indices and get desired output
out = A(lidx_2D_final);
return;
示例运行
(I)输入数组:
>> A
A(:,:,1) =
23 109 63 1 37 153
110 31 201 57 69 230
66 127 19 1 45 240
76 181 101 49 36 57
A(:,:,2) =
124 18 244 2 141 95
96 112 110 174 56 228
134 45 246 181 197 219
68 7 195 165 59 103
(II)输入参数:
>> blocksize = [2,3]; %// blocksize along rows, cols
>> stepsize = [2,2]; %// stepsize along rows, cols
(III)输出有两个版本:
>> im2col_3D_sliding_v1(A,blocksize,stepsize)
ans(:,:,1) =
23 66 63 19
110 76 201 101
109 127 1 1
31 181 57 49
63 19 37 45
201 101 69 36
ans(:,:,2) =
124 134 244 246
96 68 110 195
18 45 2 181
112 7 174 165
244 246 141 197
110 195 56 59
>> im2col_3D_sliding_v2(A,blocksize,stepsize)
ans =
23 66 63 19
110 76 201 101
109 127 1 1
31 181 57 49
63 19 37 45
201 101 69 36
124 134 244 246
96 68 110 195
18 45 2 181
112 7 174 165
244 246 141 197
110 195 56 59