---------------------------------------------------------------------------
Training stage 0
Sampled 12249 windows from 32077 images.
Done sampling windows (time=345s).
Computing lambdas... done (time=36s).
Extracting features... done (time=9s).
Sampled 25000 windows from 1024 images.
Done sampling windows (time=19s).
Extracting features... done (time=8s).
Training AdaBoost: nWeak= 64 nFtrs=5120 pos=24498 neg=25000
i= 16 alpha=1.000 err=0.226 loss=1.36e-02
i= 32 alpha=1.000 err=0.222 loss=5.68e-04
i= 48 alpha=1.000 err=0.233 loss=2.34e-05
i= 64 alpha=1.000 err=0.225 loss=8.70e-07
Done training err=0.0000 fp=0.0000 fn=0.0000 (t=7.8s).
Done training stage 0 (time=426s).
---------------------------------------------------------------------------
Training stage 1
Sampled 25000 windows from 1152 images.
Done sampling windows (time=31s).
Extracting features... done (time=9s).
Training AdaBoost: nWeak=256 nFtrs=5120 pos=24498 neg=50000
i= 16 alpha=1.000 err=0.369 loss=3.11e-01
i= 32 alpha=1.000 err=0.372 loss=1.56e-01
i= 48 alpha=1.000 err=0.370 loss=7.92e-02
i= 64 alpha=1.000 err=0.363 loss=4.18e-02
i= 80 alpha=1.000 err=0.367 loss=2.15e-02
i= 96 alpha=1.000 err=0.374 loss=1.10e-02
i= 112 alpha=1.000 err=0.375 loss=5.56e-03
i= 128 alpha=1.000 err=0.383 loss=2.89e-03
i= 144 alpha=1.000 err=0.368 loss=1.49e-03
i= 160 alpha=1.000 err=0.371 loss=7.70e-04
i= 176 alpha=1.000 err=0.363 loss=3.80e-04
i= 192 alpha=1.000 err=0.356 loss=1.89e-04
i= 208 alpha=1.000 err=0.359 loss=9.48e-05
i= 224 alpha=1.000 err=0.374 loss=4.85e-05
i= 240 alpha=1.000 err=0.353 loss=2.43e-05
i= 256 alpha=1.000 err=0.373 loss=1.24e-05
Done training err=0.0000 fp=0.0000 fn=0.0000 (t=37.5s).
Done training stage 1 (time=79s).
---------------------------------------------------------------------------
Training stage 2
Sampled 25000 windows from 2432 images.
Done sampling windows (time=57s).
Extracting features... done (time=9s).
Training AdaBoost: nWeak=1024 nFtrs=5120 pos=24498 neg=50000
i= 16 alpha=1.000 err=0.391 loss=4.53e-01
i= 32 alpha=1.000 err=0.390 loss=2.89e-01
i= 48 alpha=1.000 err=0.396 loss=1.84e-01
i= 64 alpha=1.000 err=0.396 loss=1.18e-01
i= 80 alpha=1.000 err=0.384 loss=7.62e-02
i= 96 alpha=1.000 err=0.396 loss=4.88e-02
i= 112 alpha=1.000 err=0.404 loss=3.07e-02
i= 128 alpha=1.000 err=0.397 loss=1.94e-02
i= 144 alpha=1.000 err=0.392 loss=1.22e-02
i= 160 alpha=1.000 err=0.391 loss=7.72e-03
i= 176 alpha=1.000 err=0.393 loss=4.81e-03
i= 192 alpha=1.000 err=0.384 loss=3.05e-03
i= 208 alpha=1.000 err=0.399 loss=1.95e-03
i= 224 alpha=1.000 err=0.399 loss=1.22e-03
i= 240 alpha=1.000 err=0.387 loss=7.61e-04
i= 256 alpha=1.000 err=0.396 loss=4.78e-04
i= 272 alpha=1.000 err=0.387 loss=3.00e-04
i= 288 alpha=1.000 err=0.389 loss=1.90e-04
i= 304 alpha=1.000 err=0.389 loss=1.21e-04
i= 320 alpha=1.000 err=0.392 loss=7.49e-05
i= 336 alpha=1.000 err=0.401 loss=4.71e-05
i= 352 alpha=1.000 err=0.390 loss=2.98e-05
i= 368 alpha=1.000 err=0.398 loss=1.85e-05
i= 384 alpha=1.000 err=0.391 loss=1.15e-05
i= 400 alpha=1.000 err=0.394 loss=7.05e-06
i= 416 alpha=1.000 err=0.387 loss=4.33e-06
i= 432 alpha=1.000 err=0.381 loss=2.68e-06
i= 448 alpha=1.000 err=0.396 loss=1.65e-06
i= 464 alpha=1.000 err=0.379 loss=1.02e-06
i= 480 alpha=1.000 err=0.390 loss=6.35e-07
i= 496 alpha=1.000 err=0.389 loss=3.92e-07
i= 512 alpha=1.000 err=0.389 loss=2.44e-07
i= 528 alpha=1.000 err=0.392 loss=1.51e-07
i= 544 alpha=1.000 err=0.391 loss=9.46e-08
i= 560 alpha=1.000 err=0.395 loss=5.95e-08
i= 576 alpha=1.000 err=0.386 loss=3.69e-08
i= 592 alpha=1.000 err=0.396 loss=2.28e-08
i= 608 alpha=1.000 err=0.390 loss=1.44e-08
i= 624 alpha=1.000 err=0.394 loss=8.87e-09
i= 640 alpha=1.000 err=0.388 loss=5.48e-09
i= 656 alpha=1.000 err=0.389 loss=3.40e-09
i= 672 alpha=1.000 err=0.380 loss=2.10e-09
i= 688 alpha=1.000 err=0.382 loss=1.30e-09
i= 704 alpha=1.000 err=0.389 loss=7.95e-10
i= 720 alpha=1.000 err=0.396 loss=4.75e-10
i= 736 alpha=1.000 err=0.384 loss=2.91e-10
i= 752 alpha=1.000 err=0.397 loss=1.77e-10
i= 768 alpha=1.000 err=0.383 loss=1.10e-10
i= 784 alpha=1.000 err=0.394 loss=6.77e-11
i= 800 alpha=1.000 err=0.392 loss=4.15e-11
i= 816 alpha=1.000 err=0.382 loss=2.54e-11
i= 832 alpha=1.000 err=0.402 loss=1.58e-11
i= 848 alpha=1.000 err=0.386 loss=9.62e-12
i= 864 alpha=1.000 err=0.391 loss=5.86e-12
i= 880 alpha=1.000 err=0.400 loss=3.64e-12
i= 896 alpha=1.000 err=0.390 loss=2.20e-12
i= 912 alpha=1.000 err=0.394 loss=1.37e-12
i= 928 alpha=1.000 err=0.382 loss=8.24e-13
i= 944 alpha=1.000 err=0.387 loss=5.07e-13
i= 960 alpha=1.000 err=0.388 loss=3.12e-13
i= 976 alpha=1.000 err=0.392 loss=1.93e-13
i= 992 alpha=1.000 err=0.384 loss=1.19e-13
i=1008 alpha=1.000 err=0.390 loss=7.26e-14
i=1024 alpha=1.000 err=0.387 loss=4.47e-14
Done training err=0.0000 fp=0.0000 fn=0.0000 (t=141.2s).
Done training stage 2 (time=209s).
---------------------------------------------------------------------------
Training stage 3
Sampled 25000 windows from 23360 images.
Done sampling windows (time=502s).
Extracting features... done (time=9s).
Training AdaBoost: nWeak=4096 nFtrs=5120 pos=24498 neg=50000
i= 16 alpha=1.000 err=0.408 loss=6.14e-01
i= 32 alpha=1.000 err=0.424 loss=4.47e-01
i= 48 alpha=1.000 err=0.408 loss=3.29e-01
i= 64 alpha=1.000 err=0.404 loss=2.41e-01
i= 80 alpha=1.000 err=0.407 loss=1.77e-01
i= 96 alpha=1.000 err=0.415 loss=1.29e-01
i= 112 alpha=1.000 err=0.412 loss=9.48e-02
i= 128 alpha=1.000 err=0.413 loss=6.88e-02
i= 144 alpha=1.000 err=0.403 loss=5.02e-02
i= 160 alpha=1.000 err=0.415 loss=3.68e-02
i= 176 alpha=1.000 err=0.407 loss=2.64e-02
i= 192 alpha=1.000 err=0.413 loss=1.90e-02
i= 208 alpha=1.000 err=0.412 loss=1.38e-02
i= 224 alpha=1.000 err=0.410 loss=9.94e-03
i= 240 alpha=1.000 err=0.409 loss=7.19e-03
i= 256 alpha=1.000 err=0.412 loss=5.19e-03
i= 272 alpha=1.000 err=0.404 loss=3.72e-03
i= 288 alpha=1.000 err=0.411 loss=2.65e-03
i= 304 alpha=1.000 err=0.405 loss=1.89e-03
i= 320 alpha=1.000 err=0.411 loss=1.37e-03
i= 336 alpha=1.000 err=0.414 loss=9.72e-04
i= 352 alpha=1.000 err=0.406 loss=6.99e-04
i= 368 alpha=1.000 err=0.417 loss=5.05e-04
i= 384 alpha=1.000 err=0.408 loss=3.63e-04
i= 400 alpha=1.000 err=0.404 loss=2.58e-04
i= 416 alpha=1.000 err=0.417 loss=1.84e-04
i= 432 alpha=1.000 err=0.409 loss=1.33e-04
i= 448 alpha=1.000 err=0.414 loss=9.59e-05
i= 464 alpha=1.000 err=0.418 loss=6.87e-05
i= 480 alpha=1.000 err=0.406 loss=4.96e-05
i= 496 alpha=1.000 err=0.407 loss=3.51e-05
i= 512 alpha=1.000 err=0.411 loss=2.52e-05
i= 528 alpha=1.000 err=0.418 loss=1.82e-05
i= 544 alpha=1.000 err=0.402 loss=1.28e-05
i= 560 alpha=1.000 err=0.411 loss=9.08e-06
i= 576 alpha=1.000 err=0.404 loss=6.43e-06
i= 592 alpha=1.000 err=0.411 loss=4.59e-06
i= 608 alpha=1.000 err=0.401 loss=3.21e-06
i= 624 alpha=1.000 err=0.416 loss=2.28e-06
i= 640 alpha=1.000 err=0.412 loss=1.63e-06
i= 656 alpha=1.000 err=0.405 loss=1.14e-06
i= 672 alpha=1.000 err=0.413 loss=8.13e-07
i= 688 alpha=1.000 err=0.407 loss=5.82e-07
i= 704 alpha=1.000 err=0.412 loss=4.22e-07
i= 720 alpha=1.000 err=0.411 loss=2.98e-07
i= 736 alpha=1.000 err=0.408 loss=2.13e-07
i= 752 alpha=1.000 err=0.406 loss=1.50e-07
i= 768 alpha=1.000 err=0.412 loss=1.06e-07
i= 784 alpha=1.000 err=0.410 loss=7.45e-08
i= 800 alpha=1.000 err=0.407 loss=5.25e-08
i= 816 alpha=1.000 err=0.405 loss=3.69e-08
i= 832 alpha=1.000 err=0.400 loss=2.59e-08
i= 848 alpha=1.000 err=0.415 loss=1.86e-08
i= 864 alpha=1.000 err=0.411 loss=1.31e-08
i= 880 alpha=1.000 err=0.400 loss=9.24e-09
i= 896 alpha=1.000 err=0.413 loss=6.51e-09
i= 912 alpha=1.000 err=0.411 loss=4.66e-09
i= 928 alpha=1.000 err=0.414 loss=3.32e-09
i= 944 alpha=1.000 err=0.412 loss=2.33e-09
i= 960 alpha=1.000 err=0.411 loss=1.65e-09
i= 976 alpha=1.000 err=0.396 loss=1.16e-09
i= 992 alpha=1.000 err=0.404 loss=8.31e-10
i=1008 alpha=1.000 err=0.394 loss=5.80e-10
i=1024 alpha=1.000 err=0.412 loss=4.13e
没有合适的资源?快使用搜索试试~ 我知道了~
Pdollartoolbox工具包
共675个文件
m:239个
html:186个
png:78个
需积分: 10 10 下载量 64 浏览量
2018-04-14
16:45:17
上传
评论
收藏 9.22MB ZIP 举报
温馨提示
Pdollartoolbox由UCSD的Piotr Dollar编写,侧重物体识别(Object Recognition)检测相关的特征提取和分类算法。这个工具箱属于专而精的类型,主要就是Dollar的几篇物体检测的论文的相关算法,如果做物体识别相关的研究,应该是很好用的,同时它的图像操作或矩阵操作函数也可以作为Matlab图像处理工具箱的补充
资源推荐
资源详情
资源评论
收起资源包目录
Pdollartoolbox工具包 (675个子文件)
imtransform2_c.c 11KB
meanShift1.c 5KB
histc2c.c 4KB
nlfiltersep_sum.c 2KB
nlfiltersep_max.c 2KB
assignToBins1.c 2KB
ktHistcRgb_c.c 2KB
ktComputeW_c.c 2KB
fernsInds1.c 1KB
Changelog 2KB
fibheap.cpp 20KB
gradientMex.cpp 18KB
convConst.cpp 10KB
rgbConvertMex.cpp 8KB
imResampleMex.cpp 8KB
dijkstra1.cpp 6KB
imPadMex.cpp 5KB
acfDetect1.cpp 4KB
forestFindThr.cpp 4KB
opticalFlowHsMex.cpp 3KB
binaryTreeTrain1.cpp 3KB
chnsTestCpp.cpp 2KB
forestInds.cpp 2KB
menu.css 1KB
m2html.css 1KB
m2html.css 1KB
m2html.css 1KB
m2html.css 1002B
m2html.css 1002B
Thumbs.db 27KB
simulinkicon.gif 977B
simulinkicon.gif 977B
simulinkicon.gif 977B
simulinkicon.gif 977B
simulinkicon.gif 977B
matlabicon.gif 574B
matlabicon.gif 574B
matlabicon.gif 574B
matlabicon.gif 574B
matlabicon.gif 574B
demoicon.gif 214B
demoicon.gif 214B
demoicon.gif 214B
demoicon.gif 214B
demoicon.gif 214B
new.gif 116B
new.gif 116B
.gitignore 79B
GPL 15KB
fibheap.h 3KB
sse.hpp 3KB
wrappers.hpp 2KB
Contents.html 10KB
acfTrain.html 9KB
chnsCompute.html 9KB
chnsPyramid.html 9KB
menu.html 8KB
Contents.html 8KB
Contents.html 8KB
acfReadme.html 8KB
behaviorData.html 7KB
imRectRot.html 6KB
menu.html 6KB
fevalDistr.html 6KB
bbGt.html 6KB
convTri.html 6KB
menu.html 6KB
gradientHist.html 6KB
imagesAlign.html 5KB
bbNms.html 5KB
Contents.html 5KB
binaryTreeTrain.html 5KB
nonMaxSupr.html 5KB
hog.html 5KB
opticalFlow.html 5KB
meanShiftIm.html 5KB
fevalImages.html 5KB
adaBoostTrain.html 5KB
rgbConvert.html 5KB
ticStatus.html 5KB
fernsRegTrain.html 5KB
rbfComputeBasis.html 5KB
seqIo.html 5KB
imtransform2.html 5KB
jitterImage.html 5KB
imagesAlignSeq.html 5KB
fhog.html 5KB
maskGaussians.html 5KB
kmeans2.html 5KB
overview.html 5KB
overview.html 5KB
histcImLoc.html 5KB
kernelTracker.html 5KB
histc2.html 5KB
bbApply.html 4KB
imwrite2.html 4KB
forestTrain.html 4KB
convBox.html 4KB
montage2.html 4KB
rotationMatrix.html 4KB
共 675 条
- 1
- 2
- 3
- 4
- 5
- 6
- 7
资源评论
as5560025
- 粉丝: 0
- 资源: 1
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功