error during calculating precision recall curve in Faster RCNN

Question

ahmad 2023-12-18

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/2061872-error-during-calculating-precision-recall-curve-in-faster-rcnn

回答： Gagan Agarwal 2024-1-30

在 MATLAB Online 中打开

hi everyone

i encounter this problem while finding recall precision curev how can i resolve it.error is below

Index in position 1 is invalid. Array indices must be positive integers or logical values.

Error in vision.internal.cnn.fastrcnn.detectUsingDatastore>iFindNumFiles (line 39)

numFiles = numFiles + bboxes{ii}(end,5);

Error in vision.internal.cnn.fastrcnn.detectUsingDatastore (line 28)

numFiles = iFindNumFiles(proposals);

Error in fasterRCNNObjectDetector/detect (line 552)

varargout{1} = vision.internal.cnn.fastrcnn.detectUsingDatastore(ds, this.Network, dataMap, layerOut, params);

Error in fasterRCNNtestdetect (line 39)

detectionResults = detect(detector,testData,'MinibatchSize',1,'Threshold', 0.1);

where my code is

clear
load('C:\Users\ZBook\OneDrive\Desktop\detector\detectorFasterRCNN50.mat');
dataRoad = load("D:\seg\pothole.mat");
dataRoad.gTruth
dataRoad.gTruth.LabelDefinitions
img = imageDatastore(dataRoad.gTruth.DataSource.Source);
labeldata = dataRoad.gTruth.LabelData;
blds = boxLabelDatastore(labeldata);
cds = combine(img, blds);
preview(cds)
tbl = countEachLabel(blds);
% Define the split ratios (e.g., 70% training, 15% validation, 15% testing)
trainRatio = 0.7;
valRatio = 0.10;
testRatio = 0.2;
% Count the total number of images
numImages = numel(img.Files);
% Calculate the number of images for each split
numTrain = round(trainRatio * numImages);
numVal = round(valRatio * numImages);
numTest = numImages - numTrain - numVal;
% Shuffle the datastore
cds = shuffle(cds);
inputSize = [224 224 3];
% Split the datastore into training, validation, and testing sets
trainingData = subset(cds, 1:numTrain);
validationData = subset(cds, numTrain+1:numTrain+numVal);
testData = subset(cds, numTrain+numVal+1:numTrain+numVal+numTest);
testdata = transform(testData, @(data) preprocessData(data, inputSize));
% Make predictions
detectionResults = detect(detector,testData,'MinibatchSize',1,'Threshold', 0.1);  
classID = 1;
metrics = evaluateObjectDetection(detectionResults,testData);
precision = metrics.ClassMetrics.Precision{classID};
recall = metrics.ClassMetrics.Recall{classID};
figure
plot(recall,precision)
xlabel('Recall')
ylabel('Precision')
grid on
title(sprintf('Average Precision = %.2f', metrics.ClassMetrics.mAP(classID)))
function data = preprocessData(data, targetSize)
% Resize image and bounding boxes to the targetSize.
sz = size(data{1}, [1, 2]);
scale = targetSize(1:2) ./ sz;
data{1} = imresize(data{1}, targetSize(1:2));
% Pass imageSize to helperSanitizeBoxes
imageSize = targetSize;  % You may adjust this based on your needs
data{2} = helperSanitizeBoxes(data{2}, imageSize);
% Resize boxes to new image size.
data{2} = bboxresize(data{2}, scale);
end

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Shivam 2024-1-13

Hi, Can you attach the related data for me to debug the issue?

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Gagan Agarwal 2024-1-30

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/2061872-error-during-calculating-precision-recall-curve-in-faster-rcnn#answer_1399821

Hi Ahmad,

The error message you are encountering suggests that the problem is related to indexing.

To address this issue, consider the following steps:

Verfiy the data format of the dataset and ensure that the data is correctly formatted.
Check for NaN values as there might be a case that NaN values are present in the data set.
Verify the ouput of the 'preprocess' data function to ensure that it is producing the expected results.

I hope it helps!