Error in trainFaste​rRCNNObjec​tDetector.

When I am trying to train my data into Faster RCNN using the builtin example in MATLAB (Object Detection Using Faster R-CNN Deep Learning), I got the following error message

Error using vertcat Dimensions of arrays being concatenated are not consistent.

Error in vision.internal.cnn.validation.checkGroundTruth>classHasNoBoxes (line 20) boxes = vertcat(boxes{:});

Error in vision.internal.cnn.validation.checkGroundTruth (line 10) if classHasNoBoxes(gt(:,i))

Error in vision.internal.cnn.parseInputsFasterRCNN (line 3) vision.internal.cnn.validation.checkGroundTruth(trainingData, fname);

Error in trainFasterRCNNObjectDetector (line 333) vision.internal.cnn.parseInputsFasterRCNN(...

Error in ODUFRCNNdata1 (line 124) detector = trainFasterRCNNObjectDetector(trainingData, layers, options, ...

Please help me.

N.B. I am starting with only 10 data in order to check the code (whether it runs or not with my data).

[Kanushka Gajjar]

Hi,

Did you find a solution to this? I am having the same problem.

Your assistance would be greatly appreciated!

Thanks!

Kanushka

[Fahad Parvez Mahdi]

Hi,

I cannot exactly remember now. But, maybe I got some inconsistency in my ground truth data. Can you explain me more about your dataset for example, whether you create your owen ground truth data or not?