CNN model evaluation, boxsuppress function how to reconstruct my own mask?

1 次查看（过去 30 天）
sana3 sal
sana3 sal 2018-6-6
编辑： Image Analyst 2018-6-7
Hello, I am working on object detection. I found the code here:
https://github.com/vedaldi/practical-object-category-detection
And I reached the model evaluation step.
I am having a problem with the matrix dimensions.
They use 64*64 image box and a
mask = [-1 0 1 0 ; 0 -1 0 1]
when I use 50*100 image box what should my mask be?
The code is :
function keep = boxsuppress(boxes, scores, threshold)
% BOXSUPPRESS Box non-maxima suprression
% KEEP = BOXSUPPRESS(BOXES, SCORES, THRESHOLD)
;
scores(any([-1 0 1 0 ; 0 -1 0 1] * boxes < 0)) = -inf ;
keep = false(1, size(boxes,2)) ;
while true
[score, best] = max(scores) ;
if score == -inf, break ; end
keep(best) = true ;
remove = boxinclusion(boxes(:,best), boxes, 'pascalFormat', true) >= threshold ;
scores(remove) = -inf ;
scores(best) = -inf ; % `best` is not in `remove` if threshold > 1
end
end
I tried to use .* rather than * but it still didn't work.

请先登录，再回答此问题。

回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Feature Detection and Extraction 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