我正在尝试根据50张负面图片和50张正面图片训练opencv_traincascade。我已按照此[thread][1]
中的说明进行操作。我尝试过在网上找到的不同解决方案,但无法解决问题。
我使用了这个命令
opencv_traincascade -data classifier -vec samples.vec -bg negatives.txt\
> -numStages 20 -minHitRate 0.999 -maxFalseAlarmRate 0.5 -numPos 50\
> -numNeg 50 -w 80 -h 40 -mode ALL -precalcValBufSize 1024\
> -precalcIdxBufSize 1024
我收到了这个错误
===== TRAINING 19-stage =====
<BEGIN
POS count : consumed 50 : 50
Train dataset for temp stage can not be filled. Branch training terminated.
这是培训期间生成的文本的一部分。
===== TRAINING 18-stage =====
<BEGIN
POS count : consumed 50 : 50
NEG count : acceptanceRatio 50 : 1.75143e-06
Precalculation time: 14
+----+---------+---------+
| N | HR | FA |
+----+---------+---------+
| 1| 1| 1|
+----+---------+---------+
| 2| 1| 0.48|
+----+---------+---------+
END>
Training until now has taken 0 days 0 hours 54 minutes 5 seconds.