OpenCV Error: Bad argument (Can not get new positive sample. The most possible reason is insufficient count of samples in given vec-file.

[PapaMadeleine2022]

hello, I begin to train the model. In your example, you use -numPos 68 -numNeg 140, so I use 25 for the number of pos and 55 for the number of neg. But it shows error:

---------------------------------------------------------------------------------
Training parameters are pre-loaded from the parameter file in data folder!
Please empty this folder if you want to use a NEW set of training parameters.
---------------------------------------------------------------------------------
PARAMETERS:
cascadeDirName: /home/ysju/cascade-trainer-master/classifier
vecFileName: /home/ysju/cascade-trainer-master/vec.bin
bgFileName: /home/ysju/cascade-trainer-master/negatives.txt
numPos: 25
numNeg: 55
numStages: 5
precalcValBufSize[Mb] : 1024
precalcIdxBufSize[Mb] : 1024
acceptanceRatioBreakValue : -1
stageType: BOOST
featureType: HAAR
sampleWidth: 24
sampleHeight: 24
boostType: GAB
minHitRate: 0.995
maxFalseAlarmRate: 0.5
weightTrimRate: 0.95
maxDepth: 1
maxWeakCount: 100
mode: BASIC
Number of unique features given windowSize [24,24] : 162336

Stages 0-3 are loaded

===== TRAINING 4-stage =====
<BEGIN
OpenCV Error: Bad argument (Can not get new positive sample. The most possible reason is insufficient count of samples in given vec-file.
) in get, file /home/ysju/opencv-3.2.0/apps/traincascade/imagestorage.cpp, line 158
terminate called after throwing an instance of 'cv::Exception'
  what():  /home/ysju/opencv-3.2.0/apps/traincascade/imagestorage.cpp:158: error: (-5) Can not get new positive sample. The most possible reason is insufficient count of samples in given vec-file.
 in function get

Aborted (core dumped)4

I google this error and find the common solution is about reducing the number of positive sample like link1 and link2 said. So now I am confused about the configuration of numPos and numNeg. how to solve my this error? can you give some advises?
look forward to your reply.
thank you very much~~

[ChrisTayl2018]

Hi IvyGongoogle, did you ever solve this training classifier problem? I am having the same error thrown. Thanks

[bharadwaj-vedula]

@ChrisTayl2018 have u solved the error and could you help me.

[CJSparrow]

i got same error did u solve it or not?

[SukruGokk]

I got the same error pls help

[shershunov]

To fix this, you need to increase the number of samples in the vec file, the num parameter is responsible for this.

opencv_createsamples -info positive/info.txt -vec vector/vector.vec -num 100000 -w 24 -h 24

[trezero]

To fix this, you need to increase the number of samples in the vec file, the num parameter is responsible for this.

opencv_createsamples -info positive/info.txt -vec vector/vector.vec -num 100000 -w 24 -h 24

This worked for me. Thank you

[miguelinhou]

To fix this, you need to increase the number of samples in the vec file, the num parameter is responsible for this.
opencv_createsamples -info positive/info.txt -vec vector/vector.vec -num 100000 -w 24 -h 24

This worked for me. Thank you

ME PUEDES DECIR COMO LO HICISTE?