cannot find the funcion "generateTargets"

1 次查看（过去 30 天）
xinyi shen
xinyi shen 2021-4-23
评论： arindam mondal 2022-2-22
Hello there,
I am trying to replicate the yolov3 example here. However, I cannot find a utility function, generateTargets.
which is called in modelGradients, another utility function. Please help.
I am using matlab r2021a
Thanks
% Generate target for predictions from the ground truth data.
[boxTarget, objectnessTarget, classTarget, objectMaskTarget, boxErrorScale] = generateTargets(gatheredPredictions,...
YTrain, inputImageSize, detector.AnchorBoxes, penaltyThreshold);
  4 个评论
显示 2更早的评论
MirPooya Salehi Moharer
MirPooya Salehi Moharer 2021-5-23
Thank you. I managed to fix it. Thanks for your time.
Kind regads.
Weiwei Luo
Weiwei Luo 2021-11-15
I have exactly the same issue. I am using R2020B and R2021A. Open Example does not help. I still cannot find that function. I see it is called in line 216. It was mentined before line 198. But cannot find that function. Would you possible copy it here?

请先登录，再进行评论。

请先登录，再回答此问题。

采纳的回答

Cris LaPierre
Cris LaPierre 2021-4-23
编辑：Cris LaPierre 2021-4-23
You can open this example in MATLAB using the following code
openExample('deeplearning_shared/ObjectDetectionUsingYOLOV3DeepLearningExample')
On my computer, this corresponds to the following location:
C:\Users\userName\Documents\MATLAB\Examples\R2021a\deeplearning_shared\ObjectDetectionUsingYOLOV3DeepLearningExample
When I navigate to that folder, generateTargets is there. Note that this folder is not added to your path automatically. You will need to either make that folder your current folder, or add it to your path before the example can be run. When you use the command above to open the example, it automatically changes the current folder.
  1 个评论
xinyi shen
xinyi shen 2021-4-23
Thanks!
I indeed did not find this example file indeed. But in another app, I found the functions.
Social Distancing Monitoring System

请先登录，再进行评论。

更多回答（1 个）

Weiwei Luo
Weiwei Luo 2021-11-23
I wrote the the MATLAB Support team and get the code.
function [boxDeltaTarget, objectnessTarget, classTarget, maskTarget, boxErrorScaleTarget] = generateTargets(YPredCellGathered, groundTruth,...
inputImageSize, anchorBoxes, penaltyThreshold)
% originally at the back of the mlx file as utility function
% generateTargets creates target array for every prediction element
% x, y, width, height, confidence scores and class probabilities.
boxDeltaTarget = cell(size(YPredCellGathered,1),4);
objectnessTarget = cell(size(YPredCellGathered,1),1);
classTarget = cell(size(YPredCellGathered,1),1);
maskTarget = cell(size(YPredCellGathered,1),3);
boxErrorScaleTarget = cell(size(YPredCellGathered,1),1);
% Normalize the ground truth boxes w.r.t image input size.
gtScale = [inputImageSize(2) inputImageSize(1) inputImageSize(2) inputImageSize(1)];
groundTruth(:,1:4,:,:) = groundTruth(:,1:4,:,:)./gtScale;
anchorBoxesSet = cell2mat(anchorBoxes);
maskIdx = 1:size(anchorBoxesSet,1);
cellsz = cellfun(@size,anchorBoxes,'uni',false);
convMask = cellfun(@(v)v(1),cellsz);
anchorBoxMask = mat2cell(maskIdx,1,convMask)';
for numPred = 1:size(YPredCellGathered,1)
% Select anchor boxes based on anchor box mask indices.
anchors = anchorBoxes{numPred, :};
bx = YPredCellGathered{numPred,2};
by = YPredCellGathered{numPred,3};
bw = YPredCellGathered{numPred,4};
bh = YPredCellGathered{numPred,5};
predClasses = YPredCellGathered{numPred,6};
gridSize = size(bx);
if numel(gridSize)== 3
gridSize(4) = 1;
end
numClasses = size(predClasses,3)./size(anchors,1);
% Initialize the required variables.
mask = single(zeros(size(bx)));
confMask = single(ones(size(bx)));
classMask = single(zeros(size(predClasses)));
tx = single(zeros(size(bx)));
ty = single(zeros(size(by)));
tw = single(zeros(size(bw)));
th = single(zeros(size(bh)));
tconf = single(zeros(size(bx)));
tclass = single(zeros(size(predClasses)));
boxErrorScale = single(ones(size(bx)));
% Get the IOU of predictions with groundtruth.
iou = getMaxIOUPredictedWithGroundTruth(bx,by,bw,bh,groundTruth);
% Donot penalize the predictions which has iou greater than penalty
% threshold.
confMask(iou > penaltyThreshold) = 0;
for batch = 1:gridSize(4)
truthBatch = groundTruth(:,1:5,:,batch);
truthBatch = truthBatch(all(truthBatch,2),:);
% Get boxes with center as 0.
gtPred = [0-truthBatch(:,3)/2,0-truthBatch(:,4)/2,truthBatch(:,3),truthBatch(:,4)];
anchorPrior = [0-anchorBoxesSet(:,2)/(2*inputImageSize(2)),0-anchorBoxesSet(:,1)/(2*inputImageSize(1)),anchorBoxesSet(:,2)/inputImageSize(2),anchorBoxesSet(:,1)/inputImageSize(1)];
% Get the iou of best matching anchor box.
overLap = bboxOverlapRatio(gtPred,anchorPrior);
[~,bestAnchorIdx] = max(overLap,[],2);
% Select gt that are within the mask.
index = ismember(bestAnchorIdx,anchorBoxMask{numPred});
truthBatch = truthBatch(index,:);
bestAnchorIdx = bestAnchorIdx(index,:);
bestAnchorIdx = bestAnchorIdx - anchorBoxMask{numPred}(1,1) + 1;
if ~isempty(truthBatch)
% Convert top left position of ground-truth to centre coordinates.
truthBatch = [truthBatch(:,1)+truthBatch(:,3)./2,truthBatch(:,2)+truthBatch(:,4)./2,truthBatch(:,3),truthBatch(:,4),truthBatch(:,5)];
errorScale = 2 - truthBatch(:,3).*truthBatch(:,4);
truthBatch = [truthBatch(:,1)*gridSize(2),truthBatch(:,2)*gridSize(1),truthBatch(:,3)*inputImageSize(2),truthBatch(:,4)*inputImageSize(1),truthBatch(:,5)];
for t = 1:size(truthBatch,1)
% Get the position of ground-truth box in the grid.
colIdx = ceil(truthBatch(t,1));
colIdx(colIdx<1) = 1;
colIdx(colIdx>gridSize(2)) = gridSize(2);
rowIdx = ceil(truthBatch(t,2));
rowIdx(rowIdx<1) = 1;
rowIdx(rowIdx>gridSize(1)) = gridSize(1);
pos = [rowIdx,colIdx];
anchorIdx = bestAnchorIdx(t,1);
mask(pos(1,1),pos(1,2),anchorIdx,batch) = 1;
confMask(pos(1,1),pos(1,2),anchorIdx,batch) = 1;
% Calculate the shift in ground-truth boxes.
tShiftX = truthBatch(t,1)-pos(1,2)+1;
tShiftY = truthBatch(t,2)-pos(1,1)+1;
tShiftW = log(truthBatch(t,3)/anchors(anchorIdx,2));
tShiftH = log(truthBatch(t,4)/anchors(anchorIdx,1));
% Update the target box.
tx(pos(1,1),pos(1,2),anchorIdx,batch) = tShiftX;
ty(pos(1,1),pos(1,2),anchorIdx,batch) = tShiftY;
tw(pos(1,1),pos(1,2),anchorIdx,batch) = tShiftW;
th(pos(1,1),pos(1,2),anchorIdx,batch) = tShiftH;
boxErrorScale(pos(1,1),pos(1,2),anchorIdx,batch) = errorScale(t);
tconf(rowIdx,colIdx,anchorIdx,batch) = 1;
classIdx = (numClasses*(anchorIdx-1))+truthBatch(t,5);
tclass(rowIdx,colIdx,classIdx,batch) = 1;
classMask(rowIdx,colIdx,(numClasses*(anchorIdx-1))+(1:numClasses),batch) = 1;
end
end
end
boxDeltaTarget(numPred,:) = [{tx} {ty} {tw} {th}];
objectnessTarget{numPred,1} = tconf;
classTarget{numPred,1} = tclass;
maskTarget(numPred,:) = [{mask} {confMask} {classMask}];
boxErrorScaleTarget{numPred,:} = boxErrorScale;
end
end

类别

在 Help Center 和 File Exchange 中查找有关 Data Preparation Basics 的更多信息

标签

产品

Community Treasure Hunt

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

Start Hunting!

Translated by