Revision history [back]

I have trained a haar cascade using traincascade and put -acceptanceRatioBreakValue 0.0001. The training then stopped saying that the required acceptance ratio has been reached.

===== TRAINING 9-stage ===== <begin pos="" count="" :="" consumed="" 250="" :="" 253="" neg="" count="" :="" acceptanceratio="" 10000="" :="" 5.86107e-05="" the="" required="" acceptanceratio="" for="" the="" model="" has="" been="" reached="" to="" avoid="" overfitting="" of="" trainingdata.="" branch="" training="" terminated.<="" p="">

My question is, if it is correct that the acceptance ratio is calculated for the previous stage ie stage 8 in this case, : - should I run the traincascade command again so that stage 8 is removed from the xml file?

I have trained a haar cascade using traincascade and put -acceptanceRatioBreakValue 0.0001. The training then stopped saying that the required acceptance ratio has been reached. So at stage 9,

===== TRAINING 9-stage ===== <begin pos="" count="" :="" consumed="" 250="" :="" 253="" neg="" count="" :="" acceptanceratio="" 10000="" :="" 5.86107e-05="" the="" required="" acceptanceratio="" for="" the="" model="" has="" been="" reached="" to="" avoid="" overfitting="" of="" trainingdata.="" branch="" training="" terminated.<="" p=""> NEG count : acceptanceRatio 10000 : 5.86107e-05 The required acceptanceRatio for the model has been reached to avoid overfitting of trainingdata. Branch training terminated.

My question is, if it is correct that the acceptance ratio is calculated for the previous stage ie stage 8 in this case, : - should I run the traincascade command again so that stage 8 is removed from the xml file?