MATLAB Answers

How to calculate the mse in the "bboxOffsetLoss" function in the official list yolov3?

4 views (last 30 days)
cui
cui on 4 Apr 2020
When I read the official document to detect vehicles with Yolov3, the mse in the "bboxOffsetLoss" function does not know how to calculate it. Looking at the syntax of using mse, I still don't understand.
function boxLoss = bboxOffsetLoss(boxPredCell, boxDeltaTarget, boxMaskTarget, boxErrorScaleTarget)
% Mean squared error for bounding box position.
lossX = sum(cellfun(@(a,b,c,d) mse(a.*c.*d,b.*c.*d),boxPredCell(:,1),boxDeltaTarget(:,1),boxMaskTarget(:,1),boxErrorScaleTarget));
lossY = sum(cellfun(@(a,b,c,d) mse(a.*c.*d,b.*c.*d),boxPredCell(:,2),boxDeltaTarget(:,2),boxMaskTarget(:,1),boxErrorScaleTarget));
lossW = sum(cellfun(@(a,b,c,d) mse(a.*c.*d,b.*c.*d),boxPredCell(:,3),boxDeltaTarget(:,3),boxMaskTarget(:,1),boxErrorScaleTarget));
lossH = sum(cellfun(@(a,b,c,d) mse(a.*c.*d,b.*c.*d),boxPredCell(:,4),boxDeltaTarget(:,4),boxMaskTarget(:,1),boxErrorScaleTarget));
boxLoss = lossX+lossY+lossW+lossH;
end
>>mse(3,5)
ans =
4
>> mse(3,5,1)
ans =
4
>> mse(3,5,2)
ans =
4
>> mse(3,5,2,3)
ans =
4
>> mse(3,5,2,3,10)
ans =
4
Why is this result?

  0 Comments

Sign in to comment.

Answers (0)

Community Treasure Hunt

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

Start Hunting!