que about training tif images
3 vues (au cours des 30 derniers jours)
Afficher commentaires plus anciens
hi
i need a help :
in line:rcnn = trainRCNNObjectDetector(AcneAndBeautySpots,cifar10Net, options,'NegativeOverlapRange', [0 0.01], 'PositiveOverlapRange',[0.011 0.1])
i have a error:
Error using vision.internal.rcnn.TrainingImageRegionDatastore (line 138)
Unable to find any region proposals to use as positive training samples. Lower the first value of PositiveOverlapRange to
increase the number of positive region proposals.
Error in rcnnObjectDetector/createTrainingDispatcher (line 933)
dispatcher = vision.internal.rcnn.TrainingImageRegionDatastore(...
Error in rcnnObjectDetector.train (line 223)
dispatcher = createTrainingDispatcher(detector, trainingData, regionProposals, opts, params.InputSize, params);
Error in trainRCNNObjectDetector (line 280)
[detector, ~, info] = rcnnObjectDetector.train(trainingData, lgraphOrLayers, options, params);
Error in MyRCNNObjectDetectionDemo (line 403)
rcnn = trainRCNNObjectDetector(AcneAndBeautySpots,cifar10Net, options,'NegativeOverlapRange', [0 0.01],
'PositiveOverlapRange',[0.011 0.1])
i changes the range of positive and negative proporties many times and also i removed them from thid line but still there is a error
please help me!!!!!!!!!!
I've been sitting on this code for almost two weeks trying all kinds of options but no one helps
1 commentaire
Walter Roberson
le 15 Sep 2019
"but no one helps"
I responded to your earlier question. Unfortunately your response was too vague for me to proceed.
I doubt that anyone will be able to assist without seeing your code, and a copy of any extra data beyond cifar10Net.
Réponses (1)
Voir également
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!