opencv_traincascade:无法填充临时阶段的训练数据集。分支培训终止

时间:2015-02-22 10:10:08

标签: python opencv

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.

0 个答案:

没有答案