Ask Your Question
1

RTrees::setCVFolds() causes EXEC_BAD_ACCESS

asked 2016-01-11 04:56:50 -0600

vincentfp gravatar image

updated 2016-01-27 07:55:36 -0600

berak gravatar image

Hi all,

I'm using RTrees, the new OpenCV 3.0.0 implementation. When I set the number of k-folds used for the training, I have a EXEC_BAD_ACCESS.

Any idea why ?

edit retag flag offensive close merge delete

Comments

it would be very nice, if you could come up with some minimal code example (dummy data), so folks here can try to reproduce it, next step (if it turns out to be a bug) would be an official issue here

berak gravatar imageberak ( 2016-01-11 08:52:47 -0600 )edit

This code:

auto rtrees = cv::ml::RTrees::create(); 
rtrees->setMaxDepth(depth);
rtrees->setMinSampleCount(samplecount);
rtrees->setRegressionAccuracy(0);
rtrees->setUseSurrogates(false);
rtrees->setMaxCategories(16);
rtrees->setPriors(cv::Mat());
rtrees->setCalculateVarImportance(false);
rtrees->setActiveVarCount(0);
rtrees->setTermCriteria({cv::TermCriteria::MAX_ITER, 100, 0});
//rtrees->setCVFolds(10);

rtrees->train(trainingData32F.colRange(1, trainingData32F.cols),
              cv::ml::ROW_SAMPLE, labels);

works fine. When setCVfolds uncommented it crashes during training withEXEC_BAD_ACCESS

miks gravatar imagemiks ( 2016-01-27 07:06:08 -0600 )edit

1 answer

Sort by ยป oldest newest most voted
1

answered 2016-03-16 09:23:15 -0600

miks gravatar image

updated 2016-03-16 09:23:40 -0600

Submitted as an issue 6278

edit flag offensive delete link more

Question Tools

1 follower

Stats

Asked: 2016-01-11 04:56:50 -0600

Seen: 195 times

Last updated: Jan 27 '16