F:\boost5>cd bin
F:\boost5\bin>opencv_traincascade.exe -data ../cascade -vec ../pos/sample_pos.ve
c -bg sample_negative.dat -numPos 3950 -numNeg 4479 -featureType LBP -w 24 -h 24
-numStages 15 -mem 1024
PARAMETERS:
cascadeDirName: ../cascade
vecFileName: ../pos/sample_pos.vec
bgFileName: sample_negative.dat
numPos: 3950
numNeg: 4479
numStages: 15
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 =====
<BEGIN
POS count : consumed 3950 : 3950
Train dataset for temp stage can not be filled. Branch training terminated.
Cascade classifier can't be trained. Check the used training parameters.
F:\boost5\bin>pause
请按任意键继续. . .
解决：路径问题
F:\boost5>cd bin
F:\boost5\bin>opencv_traincascade.exe -data ../cascade -vec ../pos/sample_pos.ve
c -bg sample_negative.dat -numPos 3950 -numNeg 4479 -featureType LBP -w 24 -h 24
-numStages 15 -mem 1024
PARAMETERS:
cascadeDirName: ../cascade
vecFileName: ../pos/sample_pos.vec
bgFileName: sample_negative.dat
numPos: 3950
numNeg: 4479
numStages: 15
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 =====
<BEGIN
POS count : consumed 3950 : 3950
NEG count : acceptanceRatio 4479 : 1
Precalculation time: 2.641
+----+---------+---------+
| N | HR | FA |
+----+---------+---------+
| 1| 1| 1|
+----+---------+---------+
| 2| 0.997215|0.0618442|
+----+---------+---------+
END>
Training until now has taken 0 days 0 hours 0 minutes 4 seconds.
===== TRAINING 1-stage =====
<BEGIN
POS count : consumed 3950 : 3961
NEG count : acceptanceRatio 4479 : 0.072789
Precalculation time: 2.729
+----+---------+---------+
| N | HR | FA |
+----+---------+---------+
| 1| 1| 1|
+----+---------+---------+
| 2| 0.998987|0.0707747|
+----+---------+---------+
END>
Training until now has taken 0 days 0 hours 0 minutes 8 seconds.
===== TRAINING 2-stage =====
<BEGIN
POS count : consumed 3950 : 3965
NEG count : acceptanceRatio 4479 : 0.00551266
Precalculation time: 2.679
+----+---------+---------+
| N | HR | FA |
+----+---------+---------+
| 1| 1| 1|
+----+---------+---------+
| 2| 0.999241|0.0645233|
+----+---------+---------+
END>
Training until now has taken 0 days 0 hours 0 minutes 16 seconds.
===== TRAINING 3-stage =====
<BEGIN
POS count : consumed 3950 : 3968
NEG current samples: 1173
问题：
http://villager5.blog.163.com/blog/static/8273636201462452037527/
=====
TRAINING 1-stage =====
<BEGIN
POS count : consumed 10 : 10
Train dataset for temp stage can not be filled. Branch training terminated.
Cascade classifier can't be trained. Check the used training parameters.
I took me the whole afternoon to find the solution by google, some other guys have the same problem like
me as discussed in this topic: http://answers.opencv.org/question/16868/error-in-train-casacde/
Why?
The reason is very simple, in your opencv folder, find "opencv-2.4.6.1 -> apps -> traincascade ", open
"imagestorage.cpp",
in function "bool CvCascadeImageReader::NegReader::create( const String _filename, Size _winSize )", we can see that all the image file names in negInfo.txt are read into imgFilenames by
std:getline. It seems right! But only if you have used ubuntu to generate the negInfo.txt. If you have used windows (what
I did) to generate this text file, there would be two chars at the end of each line \r\n;
on linux there is just one, \n. So,
with the original code in opencv, the \r is
kept at the end of each file name. Then, in Line 60, "src = imread( imgFilenames[last++], 0 )", the image file can't be loaded.
So, there are two solutions:
1) generate your bt.txt (negative sample file) on Ubuntu, make sure that there is a newline for each
image file no empty line in the whole file;
2) or generate your bt.txt (negative sample file) on Windows, but add one line in the original opencv
code "imagestorage.cpp":
before line 45, add "
if (str[str.size() - 1] == '\r')
str.resize(str.size() - 1); // to erase \r if the file is generated by windows"; then,
recompile (cmake .. -> make -> make install) your opencv for a new opencv_traincascade application.
解决方法：http://blog.csdn.net/forest_world/article/details/71082036
转载请注明：http://blog.csdn.net/forest_world