3D matrix time 2D matrix

2016 9 13
1 个回答
回答已采纳
更新时间：2016 9 14
9 次查看（30 天）

0 个投票

I need to do the following and I am wondering if they can be done in a much simple and efficient way.
s = size(relu);
M = s(1) * s(2);
N = s(3);
delta = single(zeros(s));
for i = 1 : s(1)
for j = 1 : s(2)
for k = 1 : s (3)
if relu(i, j, k) > 0
delta(i, j, k) = reshape(relu(i, j, :), [1, s(3)]) * gamma(:, k) / M / M / N / N;
else
delta(i, j, k) = 0;
end
end
end
end

请先登录，再回答此问题。

 采纳的回答

Andrei Bobrov
Andrei Bobrov 2016-9-13
编辑：Andrei Bobrov 2016-9-13

2 个投票

Let your gamma -> gamma1 (because gamma - name of the function from MATLAB)
s = size(relu);
M = s(1) * s(2);
N = s(3);
r1 = reshape(relu,[],s(3));
delta1 = reshape(r1*gamma1,s).*(relu > 0)/(M*N)^2;

更多回答（0 个）

类别

在 帮助中心 和 File Exchange 中查找有关 Full-Wave Analysis 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by