Modify ↓
Opened 13 years ago
Last modified 13 years ago
#8 new defect
MultiThresholdStumpLearner with TreeLearner coredumps
Reported by: | Owned by: | busarobi | |
---|---|---|---|
Priority: | major | Milestone: | Multiboost Refactoring |
Component: | Multiboost code | Version: | |
Keywords: | Cc: | balazs.kegl@… |
Description
multiboost --fileformat arff --traintest ./pendigitsTrain.arff ./pendigitsTest.arff 5 --outputinfo ./OK/REF-pendigits-TreeLearner- MultiThresholdStumpLearner-traintest.dta --shypname ./OK/REF-pendigits- TreeLearner-MultiThresholdStumpLearner-traintest.xml --learnertype TreeLearner --baselearnertype MultiThresholdStumpLearner 5 --verbose 6 --> Using learner: TreeLearner Warning: No strong learner is given. Set to default (AdaBoost). The strong learner is AdaBoostMH Segmentation fault (core dumped)
gdb output
#0 0x00000001000b001a in MultiBoost::TreeLearner::initLearningOptions (this=0x100900dc0, args=@0x7fff5fbfe350) at src/WeakLearners/TreeLearner.cpp:94 94 dynamic_cast<BaseLearner*>(_baseLearners[ib])->initLearningOptions(args); (gdb) l 89 90 pWeakHypothesisSource->initLearningOptions(args); 91 92 for( int ib = 0; ib < _numBaseLearners; ++ib ) { 93 _baseLearners.push_back(dynamic_cast<ScalarLearner*>(pWeakHypothesisSource->create())); 94 dynamic_cast<BaseLearner*>(_baseLearners[ib])->initLearningOptions(args); 95 96 vector< int > tmpVector( 2, -1 ); 97 _idxPairs.push_back( tmpVector ); 98 }
Attachments (0)
Change History (2)
comment:1 Changed 13 years ago by
Milestone: | → Multiboost Refactoring |
---|
comment:2 Changed 13 years ago by
Note: See
TracTickets for help on using
tickets.
Just to confirm that with the latest version this is still crashing at the same place.