2017-04-12 10:07:30 -0600 | asked a question | Order of sampling negative examples Lets say I have many images for negative sampling listed in the background file. But the resolution of these images is so high (720 by 1280) compared to the size of sliding window (15 by 21) that even one image quantitatively contains enough negative examples for training the whole cascade. Does this mean traincascade will sample all negative examples from the picture which is listed first in the background file? |
2017-04-07 19:04:04 -0600 | commented answer | Meaning of stages in traincascade @StevenPuttemans thanks for your comment. However it's not quite an answer to my question. What's the way of combining stumps inside one stage? Are they applied sequentially? If yes then I don't see any meaning in staging the process, because these weak classifiers themselves are working as little stages. |
2017-04-07 13:49:28 -0600 | asked a question | Meaning of stages in traincascade I'm wondering what the special meaning of stages is. As far as I understood every stage might consist of arbitrary number of classifiers depending on specified parameters of launch like |
2017-04-04 05:51:00 -0600 | received badge | ● Editor (source) |
2017-04-04 03:51:32 -0600 | commented question | training classifier freezes @berak no problem, thanks for clarifying this |
2017-04-03 18:39:01 -0600 | asked a question | training classifier freezes I posted similar question a few hours ago. After that my account was blocked without any explanations. If you are administrator and you're reading this, I hope you will at least give me a clue what's wrong with my question after deleting it second time. So here it is: I'm trying to train my own cascade for face detection in opencv using preexisting
Then the following information gets printed in the terminal PARAMETERS: cascadeDirName: data vecFileName: faces.vec bgFileName: bg.txt numPos: 100 numNeg: 50 numStages: 2 precalcValBufSize[Mb] : 1024 precalcIdxBufSize[Mb] : 1024 acceptanceRatioBreakValue : -1 stageType: BOOST featureType: LBP sampleWidth: 24 sampleHeight: 24 boostType: GAB minHitRate: 0.995 maxFalseAlarmRate: 0.5 weightTrimRate: 0.95 maxDepth: 1 maxWeakCount: 100 Number of unique features given windowSize [24,24] : 8464 ===== TRAINING 0-stage ===== POS count : consumed 100 : 100 NEG count : acceptanceRatio 50 : 1 After that nothing happens. No errors, it just freezes. It uses CPU intensively though. Any thoughts on this will be much appreciated. Thanks |