2017-09-21 09:46:38 -0600 | received badge | ● Popular Question (source) |
2014-02-12 07:48:29 -0600 | commented answer | opencv_traincascade does not seem to make any progress anymore Why does every stage take so much longer than the previous one. I think I am missing something. |
2014-02-12 04:19:38 -0600 | asked a question | opencv_traincascade does not seem to make any progress anymore Hi, When I launch this command: opencv_traincascade -data cascadeResized25 -vec resized25.vec -bg negResized25.txt -numPos 600 -numNeg 3000 -numStages 10 -featureType HAAR -minHitRate 0.99 -maxFalseAlarmRate 0.1 -w 25 -h 25 opencv_traincascade reach the stage 3 normaly, but when it try to start the stage 4, it does not continue as expected. No error message or excpetion is thrown, but it does not seem to continue ever. The last output i receive is: ===== TRAINING 3-stage ===== BEGIN POS count : consumed 600 : 622 NEG count : acceptanceRatio 3000 : 0.000661595 Precalculation time: 3.632 +----+---------+---------+ | N | HR | FA | +----+---------+---------+ | 1| 1| 0| +----+---------+---------+ END> Training until now has taken 0 days 1 hours 59 minutes 17 seconds. ===== TRAINING 4-stage ===== BEGIN POS count : consumed 600 : 622 It has been not more than 20 hours that I am "waiting" for the next stage to proceed. Any idea why ? |
2014-02-11 07:17:27 -0600 | commented answer | Traincascade Error: Bad argument (Can not get new positive sample. The most possible reason is insufficient count of samples in given vec-file. And why don't you put that formula and the result of that formula in the thrown message ... ? Would save a lot of time to a lot of people |
2014-01-30 08:27:36 -0600 | commented answer | opencv_traincascade crash without explanation Sure, the 10 and 20 was just for trying. Not I am using hundreds (and I will try thousands when I will be able to). |
2014-01-30 07:00:19 -0600 | commented answer | opencv_traincascade crash without explanation So, as said by @Median, no previous output, and changing from 100 to 25 "solved" my problem. The training does occurs, but as expected, with bad prediction result. But isn't it possible to do the training without allowing everything in the same time ? Probably not with opencv, but theoretically it is possible ? |
2014-01-30 06:55:13 -0600 | received badge | ● Editor (source) |
2014-01-30 05:50:40 -0600 | received badge | ● Student (source) |
2014-01-30 05:46:39 -0600 | received badge | ● Supporter (source) |
2014-01-30 05:46:36 -0600 | received badge | ● Scholar (source) |
2014-01-30 05:09:26 -0600 | asked a question | opencv_traincascade crash without explanation same question on stackoverflow I try to use opencv_traincascade.exe but it crashes few seconds after I launch it. Here is how I proceeded: I first create the positive sample using:
which successfully created 100 samples and then I launch the training with: And then I got the following error message: And nothing else. Any idea what is going on ? Thanks |