更新：
原文已经搬运至网站：https://www.link2sea.com/archives/383，后续也将在该网站进行更新。
查看博主更多文章请前往：https://www.link2sea.com/。
下面是原文
原文：
去年（2017年）参加robomaster时做了一段视觉，为了打大符，其实就是识别手写数字，然后控制云台射击击打制定数字。因为时间有限，而且其他部分代码都是用的C++和opencv写的，所以识别手写数字这部分代码也用C++写了。不过注意，我只写了前向计算的代码，训练的代码我没写，网络是在matlab上训练了，然后自己定义了一种存储格式存在了xml文件中，然后视觉部分的程序就是读取xml文件导入CNN，然后只做前向计算去做分类，正确率好像97%吧，其实做的很low，凑活用吧，偶然翻到了去年写的代码，写程序加调试，反正从开始左手做视觉到做完花了1个多星期吧，最后我做的视觉并没有用上，很遗憾。现在都用tensorflow了，这些代码也用不上，写篇博客就算是纪念下吧，毕竟一个多星期的心血。
下面就包括三个文件的程序，分别是 cnn.cpp，cnn.hpp 和 CNN_para.xml 三个文件。下面分别是三个文件的代码：
首先是cnn.cpp
/* SUST 陶亚凡 */
#include "cnn.hpp"
#include <opencv2/imgproc/imgproc.hpp>
#include <opencv2/calib3d/calib3d.hpp>
#include <opencv2/features2d/features2d.hpp>
#include <iostream>
using namespace cv;
using namespace std;
Mat CNN::cnnff(Mat x){
cnn_t & net = cnn;
int n = net.layers.size();
net.layers[0].a[0] = x;
int inputmaps = 1;
char str[30] = {0};
Mat z;
Mat temp;
Mat show;
for(int l=1; l<n; l++){
if(net.layers[l].type == 'c'){
for(int j=0; j<net.layers[l].outputmaps; j++){
int bias = (net.layers[l].kernelsize - 1)/2;
Size insize;
insize.height = net.layers[l - 1].a[0].rows - 2*bias;
insize.width = net.layers[l - 1].a[0].cols - 2*bias;
filter2D(net.layers[l - 1].a[0], z, net.layers[l - 1].a[0].depth(), net.layers[l].k[j][0]);
for(int i=1; i<inputmaps; i++){
filter2D(net.layers[l - 1].a[i], temp, net.layers[l - 1].a[i].depth(), net.layers[l].k[j][i]);
z = z + temp;
}
z(Rect(bias, bias, insize.width, insize.height)).copyTo(z);
net.layers[l].a[j] = sigm(z + net.layers[l].b[j]);
} // for(int j=0; j<net.layers[l].outputmaps)
inputmaps = net.layers[l].outputmaps;
} // if(net.layers[l].type == 'c')
else if(net.layers[l].type == 's'){
Mat one_mat = cv::Mat::ones(net.layers[l].scale, net.layers[l].scale, CV_32F);
one_mat = one_mat / net.layers[l].scale / net.layers[l].scale;
for(int i=0; i<inputmaps; i++){
filter2D(net.layers[l - 1].a[i], temp, net.layers[l - 1].a[i].depth(), one_mat);
net.layers[l].a[i] = Mat::zeros(temp.cols, temp.rows, CV_32F);
temp(Rect(1, 1, temp.cols-1, temp.rows-1)).copyTo(net.layers[l].a[i](Rect(0, 0, temp.cols-1, temp.rows-1)));
resize(net.layers[l].a[i], net.layers[l].a[i], Size(temp.rows/2, temp.cols/2), 0, 0, INTER_NEAREST);
}
}
}
Size sa = net.layers[n-1].a[0].size();
int a_size = net.layers[n-1].a.size();
Mat fv_tmp = Mat::zeros(a_size * sa.height * sa.width, 1, CV_32F);
for(int j=0; j<a_size; j++){
temp = MatToColumnVector(net.layers[n-1].a[j]);
temp.copyTo(fv_tmp.rowRange(j * sa.height * sa.width, (j+1) * sa.height * sa.width));
}
fv_tmp.copyTo(net.fv);
net.o = sigm(net.ffW * net.fv + net.ffb);
//cout << net.o << endl;
// Point min_idx;
// Point max_idx;
// double min;
// double max;
// minMaxLoc(net.o, &min, &max, &min_idx, &max_idx);
// return max_idx.y;
return net.o.rowRange(1, net.o.rows);
}
Mat CNN::MatToColumnVector(const cv::Mat &InputMat){
int Rows = InputMat.rows * InputMat.cols;
int Cols = 1;
Mat temp;
temp = InputMat.t();
cv::Mat OutputColumnVector(Rows, Cols, InputMat.type(), temp.data);
return OutputColumnVector;
}
void CNN::loadcnn(const FileStorage& fs){
int layers = 0;
char str[40] = {0};
int inputmaps = 1;
fs["layers"] >> layers;
fs["cnn_ffW"] >> cnn.ffW;
fs["cnn_ffb"] >> cnn.ffb;
for(int l=0; l<layers; l++){
one_layer_t new_layer;
int type = 0;
sprintf(str, "cnn_layers%d_type", l);
fs[str] >> type;
new_layer.type = (char)type;
Mat a;
if(new_layer.type == 'c'){
sprintf(str, "cnn_layers%d_outputmaps", l);
fs[str] >> new_layer.outputmaps;
sprintf(str, "cnn_layers%d_kernelsize", l);
fs[str] >> new_layer.kernelsize;
/* read k for the c layer */
for(int j=0; j<new_layer.outputmaps; j++){
vector<Mat> k_j;
for(int i=0; i<inputmaps; i++){
Mat k_ji;
sprintf(str, "cnn_layers%d_k%d%d", l, i, j);
fs[str] >> k_ji;
k_j.push_back(k_ji);
}
new_layer.k.push_back(k_j);
new_layer.a.push_back(a);
float b;
sprintf(str, "cnn_layers%d_b%d", l, j);
fs[str] >> b;
new_layer.b.push_back(b);
}
inputmaps = new_layer.outputmaps;
}
else if(new_layer.type == 's'){
sprintf(str, "cnn_layers%d_scale", l);
fs[str] >> new_layer.scale;
for(int i=0; i<inputmaps; i++){
new_layer.a.push_back(a);
}
}
else{
new_layer.a.push_back(a);
}
cnn.layers.push_back(new_layer);
}
/* for test */
#ifndef CNN_TEST
// #define CNN_TEST
#endif
#ifdef CNN_TEST
Mat x;
Mat show;
fs["test_data"] >> x;
show = x * 255;
show.convertTo(show, CV_8U);
transpose(show,show);
imshow("input pic", show);
int t1,t2;
t1 = cv::getTickCount();
int ans = 0;
// ans = cnnff(x);
cout << "ans = " << ans << endl;
t2 = cv::getTickCount();
cout << "Consumer-Time: " << (t2 - t1) * 1000.0 / cv::getTickFrequency() << "ms" << endl;
waitKey(0);
#endif
}
Mat CNN::sigm(Mat P){
exp(-P, P);
return 1/(1 + P);
}
接着是cnn.hpp：
/* SUST 陶亚凡 */
#pragma once
#include "opencv2/core/core.hpp"
#include "opencv2/highgui/highgui.hpp"
#include <vector>
#include <utility>
using namespace cv;
class CNN {
public:
typedef struct one_layar {
char type;
std::vector<cv::Mat> a;
std::vector<float> b;
int outputmaps;
int kernelsize;
std::vector<std::vector<cv::Mat>> k;
int scale;
}one_layer_t;
typedef struct cnn{
std::vector<one_layer_t> layers;
cv::Mat fv;
cv::Mat ffW;
cv::Mat ffb;
cv::Mat o;
}cnn_t;
public:
CNN();
CNN(const std::string & filename){
FileStorage setting_fs(filename, FileStorage::READ);
loadcnn(setting_fs);
setting_fs.release();
}
cnn_t cnnreturn(){return cnn;}
cv::Mat cnnff(cv::Mat x);
protected:
void loadcnn(const cv::FileStorage& fs);
cv::Mat MatToColumnVector(const cv::Mat &InputMat);
cv::Mat sigm(cv::Mat P);
private:
cnn_t cnn;
};
最后是存储CNN结构的xml文件的数据，其中还包括一个例图28*28的：
<?xml version="1.0" encoding="utf-8"?>
<opencv_storage>
<layers>5</layers>
<cnn_ffW type_id="opencv-matrix">
<rows>10</rows>
<cols>192</cols>
<dt>f</dt>
<data>-0.568684 -0.840148 -0.454545 -1.318691 -0.542536 0.262243 -0.190369 0.188239 0.168000 0.150902 -0.776808 0.276366 0.932940 -0.352636 0.049857 -0.016501 -1.307408 0.418510 1.703576 -0.275972 0.327144 -0.138172 -0.276332 -0.283987 0.166491 -0.427241 -0.047831 -0.288850 1.384224 0.820337 -0.152349 -0.619389 -0.179057 0.390203 0.915956 0.663474 -0.632854 -1.023481 -0.569145 -0.551961 0.050373 -0.443177 -1.381474 -1.862783 1.142882 1.096406 0.173264 -1.261844 -0.127105 0.177692 0.322486 -1.689607 -1.103839 -0.474490 -0.396990 -0.919875 -1.812920 0.095724 -0.548418 -0.263181 -1.279738 0.837480 2.166042 2.395184 0.039804 -0.517603 0.383755 0.961707 0.718807 -0.990300 0.508205 0.767228 -0.249060 0.790682 0.780152 -0.349029 0.356309 0.664598 0.612107 -0.952957 -1.162191 -0.413933 -0.007629 -1.119251 -1.785648 -0.975712 -0.808158 -0.878558 -1.913150 -0.696603 -1.048091 -0.554665 -0.998564 -0.749730 0.560802 1.071287 -1.263524 -1.357791 -0.382083 -0.438742 -0.147290 -0.472937 -1.144568 1.020860 -0.386209 -0.904939 1.490753 1.583735 0.351348 -1.353244 -0.017483 1.558953 0.123887 0.572187 -0.513296 -1.274787 1.160012 0.325008 -0.453308 -1.265027 1.114152 -0.706548 -0.857605 -0.830754 0.010065 -0.484612 0.113302 0.800446 0.011397 0.450172 -0.345578 -1.867464 0.983451 -0.304089 -0.519521 -1.146774 -0.291938 -0.025131 -1.005695 -0.154603 -0.961208 -0.318354 0.332191 0.746977 0.017100 0.971496 0.350664 -0.247105 0.442959 -0.954869 -0.197612 -0.769494 -1.617853 -0.873141 -0.186129 0.185366 -1.805443 -0.410434 0.504179 -0.039253 0.344962 0.670727 0.746010 0.827250 -0.366512 -1.378792 -1.921945 -0.581498 -0.683050 -1.075891 -0.485163 -0.795280 -0.115390 -0.277790 1.091993 1.596517 -0.288662 -0.174590 0.381413 -0.776837 -0.774400 0.082224 -1.847365 -1.367115 -1.071762 -1.154800 -0.430710 0.187430 -0.981025 0.173648 0.619034 0.395178 0.670848 -0.190562 1.578060 1.081296 -0.568814 0.058157 0.686897 -0.635822 0.900271 0.439748 0.697416 -0.387801 -0.518810 0.290915 0.350912 -0.715028 -1.647098 -2.401533 -2.408404 -0.715723 -0.580959 0.128428 -0.738845 -0.865536 -0.780717 -0.422889 -1.387967 0.936520 0.654036 -0.850674 0.481915 -0.885330 0.151825 -0.003216 0.113889 0.895744 -0.334037 -1.075032 0.259564 -0.049494 -0.467224 -2.171169 0.044801 0.352682 0.169473 0.207688 1.986277 1.080322 0.031921 -0.064943 0.291739 -0.384199 0.443816 -0.678896 -0.149150 -0.103646 0.606457 -0.851627 0.666114 0.470407 0.326996 0.171576 0.866813 -1.323896 -0.896076 2.009523 1.870687 -0.088985 0.150642 0.732542 -0.415214 0.096963 -1.214229 -1.938633 0.411621 -1.070952 0.057377 -2.841435 -0.297376 0.690975 -0.864447 -0.928141 -0.510805 -0.883791 -0.459018 -0.859915 -1.351250 -1.154162 -0.298049 -2.317568 -0.768941 -0.665157 -1.651614 -0.661028 -0.192331 -0.302086 -0.063164 0.661084 0.988643 0.628787 0.061343 -1.064286 -0.399700 0.003194 -0.586815 0.845286 -0.440110 0.007938 -0.716887 1.713239 -0.470617 -0.644067 -1.051352 1.370634 0.377730 1.402900 0.152722 0.469785 -0.354833 -0.164888 0.177156 1.002260 -0.598730 -0.687314 0.602623 0.339472 0.684160 0.383501 0.670998 -0.209076 0.135982 0.173958 0.076611 1.078072 -0.646387 0.351450 0.496793 0.754224 0.023728 0.604938 1.085749 0.952455 0.258260 -0.911355 -0.461454 -0.284038 1.916496 1.390354 0.950783 1.991596 -0.027214 0.753137 0.845360 0.499624 0.201375 1.444512 0.830598 0.161795 0.984455 0.709851 0.102322 0.832743 -0.137935 -2.126368 -1.093201 0.316729 -0.345943 -0.667056 -0.668533 0.954747 -0.592794 -0.622690 1.710437 1.086969 -0.121517 -1.767624 -0.193522 -1.277201 -2.141669 -0.783888 0.709102 -0.584764 -1.178761 -1.046521 -0.500537 -1.407760 -1.456903 -1.166710 0.114529 -1.222344 -0.485937 0.366948 0.678354 0.881663 -1.885476 -1.764005 -0.574188 0.999854 -0.375238 -1.371269 0.284578 -1.017808 0.163411 0.149505 1.415138 1.614423 2.244284 1.782228 -1.215948 0.959955 -0.236855 -2.091445 -0.425496 0.373386 -1.719937 -1.513815 -0.480159 0.293449 -1.128259 -0.109912 -1.335769 -0.414058 2.265155 3.415650 -0.462177 1.326707 0.814925 0.393905 0.579491 0.613182 -0.108630 -0.614807 -1.861581 -1.632298 0.396614 -0.919935 -1.208531 0.535476 1.987387 1.474315 0.702240 0.918989 -0.236851 -1.880555 1.675656 0.526113 -0.359203 1.523022 1.762864 0.422372 0.828221 0.258063 0.032520 2.631290 0.444756 -0.210713 -1.560551 -0.438164 -0.160917 -1.351426 -0.961034 -1.900673 -0.934203 -0.572908 0.472002 0.265572 0.399855 -0.221858 0.620770 2.063923 1.105910 0.108550 0.081312 0.092552 -0.589873 -1.328607 2.411575 0.019260 -1.319895 -0.496505 -1.256033 -1.149169 -0.300088 0.803819 -1.205085 0.152804 -0.190873 1.999035 0.262617 -1.265177 -1.926570 -0.850561 -0.071587 -0.322788 -0.481424 -0.532940 -0.287171 -1.247944 1.320629 0.277887 0.361195 -1.152884 -2.887138 -1.550886 -0.365399 0.083547 -0.735211 -2.018912 0.055647 -1.070096 -0.807210 -0.741435 1.793538 0.538075 -0.096737 1.292373 1.647268 0.869284 0.188351 0.191427 0.180810 0.663445 -0.998189 -1.756560 0.431852 1.402694 1.247088 0.235649 0.025021 -1.903438 -0.063016 0.435442 -1.837954 -0.968299 -1.118530 -0.990334 0.519120 -0.820571 -0.407835 -0.238509 0.314300 1.376042 -0.030988 -0.271011 0.902175 0.178550 -0.537286 -0.722177 -2.392766 -0.244671 0.928415 0.731318 -1.323398 -1.728493 0.730880 -0.846633 1.481762 1.500963 2.334629 0.828116 0.365176 -1.337337 1.031938 0.956734 0.798765 -0.938663 0.000748 -0.134341 0.025908 0.644007 0.996969 -0.548298 2.046839 0.998907 -0.701453 -0.971052 1.675005 0.871147 -0.244738 -1.120503 -0.323273 0.596829 0.669091 0.954019 -0.860371 -1.386022 -0.392221 0.243332 -0.241974 -0.683338 -0.147636 -0.069763 0.539730 -0.502065 0.660576 0.272680 -0.973756 -2.302124 -1.806688 -1.397432 1.978154 -0.381901 -3.991838 -3.267560 -0.813706 -0.035162 0.358718 0.067427 -1.571896 0.745802 0.883409 -0.832795 -1.015582 -0.339173 -1.485606 -1.993328 0.446727 0.261968 -0.165605 0.148824 -2.105331 -2.298861 0.111934 -0.327436 -0.391297 -0.006948 -0.276133 0.201642 0.957007 0.301777 -0.292803 -1.836007 1.033090 0.329261 0.585537 -0.330559 0.734589 -0.083318 -0.076891 -1.006984 -0.483244 -0.623377 -0.131023 -0.349660 0.582504 2.046764 1.477527 1.297367 -2.903940 -0.591571 -0.327045 0.253036 -2.512030 0.566448 -0.392588 -1.427930 -1.156357 -0.394138 0.632693 -0.102152 0.101450 0.362274 0.258531 -0.243339 -0.527029 0.125557 0.196156 -3.057717 1.675665 0.089363 -0.379145 -0.750548 0.565219 0.332144 0.117553 -0.737922 1.753175 1.119900 -0.796398 -2.461310 -0.470098 1.862193 1.158181 1.364021 0.696346 2.222303 1.930120 0.721784 0.196732 0.628445 -1.654194 0.016938 0.891370 0.686571 0.253569 1.771295 -0.675412 -0.133967 -1.084868 -0.999840 0.491990 0.192794 1.088356 1.439274 -1.222168 -1.789202 -1.625279 -0.801888 -1.797137 -0.911832 0.065790 -0.658735 0.497864 1.294581 -1.006325 -1.784692 -0.197554 1.582629 -0.409572 -0.614467 1.161009 -0.040161 -2.042802 -0.994689 1.159896 1.090596 0.053673 -0.937990 1.209290 -1.319139 -0.584847 -1.007999 0.044495 0.224670 -0.501834 -0.771122 -0.111253 -0.072331 -0.081031 -1.860726 1.915827 1.763340 -0.189091 -1.738653 -0.495736 0.565919 1.570264 -0.254456 1.944117 1.445322 -0.692396 1.405102 1.740337 0.033836 -2.188582 0.814919 0.711882 -0.398001 0.568906 2.166097 2.190312 1.968536 -0.247265 0.129662 3.128374 1.174358 0.512820 1.190940 1.224998 1.370482 1.260627 0.059600 1.799410 1.919784 1.911546 0.801935 -0.227641 -0.161793 0.203008 -0.093949 -0.048898 0.137546 0.235772 -0.505766 -0.141896 0.376557 -0.360899 0.374750 0.207676 0.262211 0.021811 -0.114356 0.472937 -2.555414 -1.220176 -0.008920 -0.266338 -1.011427 0.408339 -0.467615 0.234892 0.573901 0.342198 0.820410 0.210724 0.287283 0.180946 0.358511 -0.208742 -2.123883 -2.371194 -3.221006 0.298170 0.921410 0.032602 -0.804788 1.686209 2.216388 0.970906 1.353232 -1.856343 -1.628873 -0.242889 0.521827 -0.095297 -0.572879 -0.288382 -1.309608 -1.280254 -0.291324 -0.228825 -0.135539 0.254940 -0.605391 0.144381 0.381320 -0.696364 -0.935940 -1.432375 -2.161635 1.876899 1.425327 1.543814 1.796160 1.391074 -0.352236 0.603197 0.038896 -0.498047 -1.267728 -0.739036 -0.141810 -0.231306 -2.165954 -2.270451 -0.969459 -0.828693 -0.541079 -0.875633 -1.014755 -0.829627 -0.190832 -0.825192 -0.465526 -0.303846 2.242185 2.871771 1.746162 -0.025536 0.315838 0.190072 -0.340349 0.437247 2.051160 2.753477 3.670743 1.116912 -0.237859 0.070147 0.066850 -1.243604 -0.782650 0.640205 -0.443454 -0.927431 0.232213 1.017170 0.650477 -0.139963 -1.461932 -1.507187 0.459397 -0.150864 0.088782 0.151170 0.255476 0.561128 -1.060071 0.955530 0.102883 -0.405562 0.146712 0.063084 -0.807549 -0.485626 -0.629333 -0.141298 -0.392197 0.936452 -0.177624 -1.471338 0.221610 -0.016912 -0.000844 0.324053 1.104399 -1.567034 -0.795029 -0.794306 -0.562836 -1.999496 -1.921080 -1.547621 -0.748640 0.649149 -0.839418 0.045959 -0.424026 0.553456 0.157773 0.833560 -0.204587 1.144696 -1.063715 -0.932452 0.173564 0.848306 2.379786 1.154657 -1.456662 -0.669313 0.894472 -0.523726 -0.993333 -0.144151 -1.768133 1.589102 -0.644753 0.755671 0.001717 -0.444305 -1.595350 -0.695945 -3.403769 -2.334792 -1.455888 -0.439346 -0.632650 -0.621456 0.012967 0.123181 -0.438825 0.260000 1.110785 0.029384 -0.827939 -1.363545 0.202975 1.393832 -0.125447 -0.602895 0.073965 -0.772413 -0.102117 -1.248192 -1.010682 -0.810522 -0.092139 -0.620883 0.122056 -0.041539 -0.308564 0.209445 -0.163835 -3.143505 -1.031206 1.457171 2.302944 -0.781428 0.437319 0.350226 1.811430 0.442485 -0.180263 -1.022792 -0.986391 0.911063 0.181654 -0.893159 -1.333278 -0.826237 0.017838 0.634340 -1.070578 2.160331 0.065067 0.010424 1.540661 0.781623 0.081265 0.941142 0.986001 0.094109 -0.801980 -0.406743 0.304223 -1.440977 0.181139 0.771358 -0.235621 -0.530992 -0.169878 -1.112803 1.290390 -0.379169 -0.955182 0.731747 0.250877 2.108353 1.977838 1.218618 -0.024520 0.459867 -0.168090 0.041903 -1.941308 -0.324973 -1.307380 -1.337884 -0.495968 -0.344612 -0.438792 -0.053327 -0.472847 -0.009257 1.451169 1.164124 -0.523420 -1.840840 0.421446 1.414480 2.648293 0.900559 0.104310 0.384247 2.741474 1.576432 0.699755 -0.432687 -0.435650 1.080107 0.712610 -0.616311 -1.727864 0.349881 -2.490028 -1.889569 0.155122 -0.334565 -3.644602 -4.750808 -3.863300 -1.165815 -1.212192 -1.349019 -2.309642 1.344263 1.080357 0.000613 0.307156 -0.762989 0.722342 0.324666 1.172601 -1.484892 -0.910311 -0.191652 -1.304129 0.065768 -1.381948 -2.140570 -2.276532 -0.024935 -0.128392 -0.580782 -1.047196 0.115238 0.136203 1.375095 2.202972 0.551549 -0.957728 -1.228891 -1.545077 0.581161 -0.253539 -0.289483 -0.059607 1.570291 -0.168237 0.383992 0.223900 -1.866155 0.559566 1.454097 -0.399695 -0.158108 0.003398 -0.031452 0.567360 0.438583 0.387090 0.595258 -0.200034 0.656961 0.891128 0.958617 -0.312642 -0.343202 -0.355542 -1.639507 -0.380261 -0.505060 -1.627764 -1.777507 -0.243594 1.601325 0.442811 0.405539 -0.368260 0.051375 1.553478 0.933744 1.156198 -1.800796 -1.046701 0.490339 1.050771 -0.254181 0.056763 0.900632 0.085808 1.834519 0.170169 -0.409959 0.434842 2.612757 1.610709 0.409695 0.316207 -0.547553 0.096064 0.766504 0.125843 0.219115 0.586405 0.195862 -0.072568 0.294727 0.216496 -0.173536 -1.186730 0.312519 -0.536973 0.022352 -0.166393 -1.231942 -1.381445 -1.137722 -0.333346 -0.882915 -0.076861 1.315101 -0.310112 -0.682046 0.125003 1.037291 -0.483653 0.873564 0.530456 0.526258 -0.862902 -1.066475 -1.218495 -1.659488 -0.609078 -1.389337 -0.949065 0.306276 1.760333 -1.391450 0.085452 -0.123883 -0.965901 0.111994 0.770534 0.675396 -0.416215 -1.204105 -0.375743 0.345809 1.003884 -1.020946 0.706154 0.787437 -0.065904 -1.384291 -0.335952 -0.391686 -0.429979 -1.397392 -0.862799 0.268035 0.850149 1.067515 1.398698 -0.498010 -2.371799 1.798114 1.251210 -1.168329 0.291684 -0.559087 0.706142 -0.025673 -0.210420 -0.965674 0.168686 0.769225 -0.351589 -1.046891 -1.280924 -0.389689 0.150468 -1.581234 -0.550692 0.519401 0.914398 -2.749731 -1.423537 -0.363503 -1.278083 -0.272173 -0.624108 0.542652 0.019914 -0.314182 -0.260372 0.891326 -0.660829 -0.770017 0.088855 -0.084554 -1.685748 -0.255018 -0.126376 -0.642861 0.093575 0.267771 -0.015112 -0.625179 -0.138345 0.010329 0.419641 1.186201 0.258952 0.534138 0.754038 0.693424 0.294210 -0.453652 0.566203 -0.529290 -0.163980 -0.559476 0.256946 0.489759 0.796553 -1.128798 0.057303 1.454473 0.919689 -0.496402 -0.106569 1.066809 0.262154 -1.364907 -0.543781 0.027583 -1.254330 -1.575480 -0.660659 -0.555377 -0.070598 0.179412 0.107627 0.339767 1.444431 -0.096725 0.489460 -0.195903 1.114815 -2.302524 -0.388951 -0.654427 -1.372961 -0.969152 -0.879160 -0.203950 -1.423161 -0.041881 -1.222031 -2.201077 -0.325509 0.341469 1.042031 -0.169064 0.067367 -0.640211 1.265755 0.275049 1.303543 -0.532226 -0.295897 -0.498129 1.165844 -0.772748 -1.255129 -0.462340 0.259145 -0.788304 -0.958496 1.350558 1.679458 -2.053554 -0.549383 0.547350 1.319393 -1.232782 0.183773 1.151964 0.235622 -0.323954 -0.938132 -0.440117 -0.059274 -1.471364 0.527611 -0.207397 -0.465747 -0.698038 1.595036 -0.366103 -0.123031 0.799492 1.199440 -0.611368 -0.065947 -0.160355 0.274492 -0.874488 -1.364047 0.864203 -0.865951 0.329187 0.479050 1.436393 -2.617084 0.414072 0.657742 -1.268740 -1.692483 -0.927944 -1.525618 1.614777 1.251504 1.076180 0.275388 0.510664 -2.395774 -0.340014 0.003076 -0.825435 -2.820573 0.288718 1.258191 -1.942397 -1.937704 -0.683860 -1.399690 -0.451199 0.592533 0.407767 -0.195370 -0.950124 0.221049 -1.360520 -0.198462 0.936981 -0.800861 0.784768 0.784122 1.029617 -2.045210 -1.240094 -0.522609 -0.769536 -1.495526 -1.119689 0.044535 -1.490488 -1.234936 -1.388229 -1.048332 -1.434484 -0.108756 0.996262 -0.382807 -1.194693 -2.984174 -1.671952 -1.148140 2.229082 1.613030 1.056897 0.181968 0.813897 -0.765012 0.114626 0.118422 0.012888 -2.640741 0.385381 1.481545 -1.044656 -1.755256 0.161362 -0.188742 -1.493274 -2.124631 1.255714 0.998933 -0.935014 -0.382784 -0.237472 0.303672 0.646053 1.417229 0.365469 0.406790 0.750101 0.709007 1.106474 -0.155063 -0.929856 -2.272413 0.514496 0.240403 -0.346942 0.615023 -2.438864 0.429499 0.222819 -0.070867 1.257759 0.102763 -0.865200 -0.684704 -0.003359 0.942360 -0.398605 0.885533 0.462080 0.515423 0.325545 0.061010 -0.709412 0.341276 1.223137 -0.009923 1.202514 -0.167596 1.827646 0.387063 0.270697 0.536398 -0.708280 1.826727 1.441355 1.586354 1.143942 -0.548775 -0.494202 0.672445 -0.043321 0.576371 1.920968 -0.499610 0.952112 -1.455865 -0.432408 0.495391 1.442865 1.310892 -0.445348 0.653455 0.920869 0.891832 0.358409 0.073444 1.868516 0.956122 2.085441 -0.095860 0.472699 -0.441179 -0.913885 -2.024397 -0.296077 0.386462 1.627353 1.730042 0.255146 0.633769 -0.264000 0.244754 0.499053 -1.431312 -0.581804 0.220206 -0.623001 -1.356150 -1.753298 -1.491591 0.345923 -0.433372 -0.465977 -0.558850 -0.799986 -2.006180 -1.024080 0.319769 -0.613227 -0.359395 -0.650162 -0.985309 3.129141 1.913143 -0.513350 -1.044233 -0.108263 1.863723 0.710110 -0.030438 1.078815 1.091301 0.261748 0.393061 0.588950 1.753919 2.519222 1.751516 0.625041 0.009376 -1.801419 -1.632986 -0.506030 0.675085 -0.743360 -0.801761 1.762069 1.404480 -0.104017 -1.995480 -0.495086 2.137743 0.480064 0.563456 -0.267995 -0.524163 -0.190528 -1.470629 -0.844243 -1.694800 -0.982685 -1.208962 -1.858653 -2.114876 0.492831 -0.172904 -0.662782 -0.120788 2.551433 -1.092450 -2.132823 -1.345203 1.068296 1.088921 -0.406751 0.394294 0.884560 -0.482774 -0.214612 0.315526 0.328038 -0.228823 0.268250 0.114338 2.056436 -0.224052 0.360794 1.699486 2.536694 0.036895 -0.710604 -1.249225 -0.328610 -0.898870 -1.643944 -0.958242 -0.697438 0.283124 -1.226860 -1.664179 0.998384 0.440117 -1.471759 -1.062178 -1.373420 -1.183465 -0.461257 0.854288 -0.647952 0.001883 -0.300862 1.235110 0.576967 2.763716 -0.333809 0.357859 -0.901208 -1.286400 -0.333899 -0.242820 -1.004977 0.478535 0.101815 0.264443 -0.262787 -0.892422 -0.792109 -1.311681 1.504840 1.478679 1.467973 2.500284 1.172229 0.154042 1.294795 0.004448 -1.561644 -1.024204 0.202930 -0.497275 -1.716917 0.327054 -0.894834 -0.761311 -1.736770 -0.951662 -1.168343 -0.656708 -0.456710 -0.501793 -2.070152 -2.946447 -0.069577 0.873284 -0.405397 -0.810348 -0.023117 -1.808209 -1.769730 -1.313330 -1.396610 -1.700187 1.608046 -0.963677 -2.151605 -0.165684 -1.608762 -1.417427 -1.008753 -1.473954 -0.562654 -1.367941 -0.565165 -1.031487 -2.555339 -0.948666 0.169501 0.719535 -3.096711 0.080337 0.749237 -1.553453 -0.624246 -1.065132 -1.504511 0.607266 0.051752 1.381952 0.779319 1.524857 0.383780 0.730565 0.950426 0.791245 -0.160060 -0.139976 1.241984 0.651157 -0.422804 -1.211516 0.188107 1.631316 0.146122 -0.639282 0.020875 0.900917 0.647986 0.347648 0.123858 0.070550 -0.305496 -2.253028 0.645869 -0.432195 -1.673982 -1.362609 1.276769 -1.050025 -0.623815 4.927931 1.866003 -1.121364 0.283773 -0.467816 -1.391952 -2.374363 0.866782 1.747543 -1.019442 -1.185769 0.959649 0.069812 -0.599814 0.105262 -2.148772 0.570878 1.374298 2.523965 -0.286523 -0.218409 1.287989 -0.740257 1.371606 -0.047983 -2.163101 -2.245314 -0.522199 -1.285056 -1.875885 0.623396 0.012222 0.480420 0.471406 -0.538771 -2.195949 -1.248463 0.932432 -0.701189 -0.252414 1.592603 0.282323 0.790642 1.760016 0.211087 -0.138736 -1.436672 0.822336 0.195795 0.911973 -0.282352 1.834799 1.350915 0.776758 0.849426 1.067250 0.332330 -2.779764 0.493876 0.264206 -1.145561 -3.171683 -1.171062 -1.103135 -0.809399 -1.155126 -0.813583 0.344989 1.545957 -0.250092 -0.811063 0.089158 1.718029 -0.753593 -2.121455 1.780892 1.365310 -1.537077 -1.240571 0.158582 -0.262367 -2.235570 -3.342456 0.292023 0.660051 -0.027997 0.354088 -0.267050 0.137872 1.228981 0.353140 0.030013 0.586983 1.136264 -0.228273 0.780281 1.657217 0.865480 -0.292382 0.369480 -0.150166 2.639763 0.231222 -3.313885 0.298308 -1.182134 1.278971 -1.279189 -1.400231 -0.611965 -0.521085 -0.558140 -0.713025 0.481648 -0.947564 -0.341289 0.306766 0.566019 -0.639597 -1.682999 -0.410302 -0.233620 -0.227329 0.178344 0.542107 0.321821 -0.474126 0.533247 0.881646 -0.171466 -0.534541 -2.794765 -1.133443 -0.340685 -0.206887 -0.979014 -0.131371 -1.381110 -0.328498 0.438844 -0.415387 -1.617667 0.326309 -2.019398 -2.924026 -0.283484 1.197003 -0.849612 -1.564040 -0.656327 0.720076 -3.061249 -0.445999 -1.019625 -1.541968 -1.268363 1.080393 1.393301 -1.995058 0.477826 3.215140 1.667473 1.111687 -1.311818 0.593499 1.027178 0.360190 -2.084913 0.445291 0.480524 -1.490454 0.535803 1.217250 -0.922550 -2.921451 </data>
</cnn_ffW>
<cnn_ffb type_id="opencv-matrix">
<rows>10</rows>
<cols>1</cols>
<dt>f</dt>
<data>-0.208850 0.266063 -0.704551 -1.283109 -0.180354 -0.619580 -0.535265 -0.298749 -0.421863 -0.348450 </data>
</cnn_ffb>
<cnn_layers0_type>105</cnn_layers0_type>
<cnn_layers1_type>99</cnn_layers1_type>
<cnn_layers1_outputmaps>6</cnn_layers1_outputmaps>
<cnn_layers1_kernelsize>5</cnn_layers1_kernelsize>
<cnn_layers1_k00 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.887788 0.842190 0.417631 -0.715789 -1.638689 0.640878 1.951005 2.146345 1.380077 -1.490390 1.352646 1.955425 2.200980 1.354717 -1.293385 0.911197 2.210627 2.065331 1.422653 -1.049191 -1.740300 -0.001076 -0.070818 -2.165646 -2.397248 </data>
</cnn_layers1_k00>
<cnn_layers1_b0>-1.609968</cnn_layers1_b0>
<cnn_layers1_k01 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.437037 1.794848 1.023498 0.542444 1.293184 1.786401 0.663311 -1.678167 -1.320248 -0.463482 2.747359 -0.622984 -2.747748 -1.870434 -0.916018 2.405787 -1.090972 -1.947285 -1.113549 -0.821563 2.727311 1.580017 0.562813 -0.139603 -0.561097 </data>
</cnn_layers1_k01>
<cnn_layers1_b1>-0.594352</cnn_layers1_b1>
<cnn_layers1_k02 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-1.553613 -2.637853 -0.740015 -0.501383 -2.585971 -1.953611 0.407394 2.373196 1.713361 -0.969999 -1.184779 2.001626 2.500187 1.917731 -0.854430 -1.073362 1.616814 1.485564 1.197744 -0.922041 -1.199136 0.951369 2.253879 2.007004 -1.234090 </data>
</cnn_layers1_k02>
<cnn_layers1_b2>-1.343453</cnn_layers1_b2>
<cnn_layers1_k03 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-1.020622 -0.247964 2.204377 2.872920 0.313683 -1.638356 -0.295532 2.085941 2.629840 -0.558158 -1.397051 -0.092971 1.313041 3.330445 -0.606560 -1.030561 -0.749874 1.157594 3.358993 -1.022623 -1.129144 -0.951804 1.289253 3.060025 0.402815 </data>
</cnn_layers1_k03>
<cnn_layers1_b3>-0.521210</cnn_layers1_b3>
<cnn_layers1_k04 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.527269 -0.861980 -0.776762 -0.975689 0.138755 -0.555069 -0.797630 -1.516494 -2.147861 -0.868947 -1.259052 -2.271856 -1.752028 -1.208592 0.269151 -2.328819 -2.221908 -1.250354 -0.278160 1.213085 -0.929328 -0.350707 0.721657 1.936334 2.846669 </data>
</cnn_layers1_k04>
<cnn_layers1_b4>0.080604</cnn_layers1_b4>
<cnn_layers1_k05 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.166197 -1.290959 0.385633 1.444009 0.346965 -0.413110 0.291724 2.174643 2.180627 -0.143787 -1.232905 1.612843 2.351108 -0.250272 -1.796086 -0.751216 2.148606 1.657975 -1.107557 -1.122619 0.020527 1.376726 0.405629 -1.314767 -1.316237 </data>
</cnn_layers1_k05>
<cnn_layers1_b5>-4.719292</cnn_layers1_b5>
<cnn_layers2_type>115</cnn_layers2_type>
<cnn_layers2_scale>2</cnn_layers2_scale>
<cnn_layers3_type>99</cnn_layers3_type>
<cnn_layers3_outputmaps>12</cnn_layers3_outputmaps>
<cnn_layers3_kernelsize>5</cnn_layers3_kernelsize>
<cnn_layers3_k00 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.342219 -0.025249 0.088651 -0.034061 -0.878626 0.726322 0.578896 -0.422382 -0.678117 -0.079399 0.880338 -0.305906 -1.050583 -1.112874 -0.496037 -0.132832 -1.338326 -0.767557 -0.853697 -0.489092 -0.140113 0.091994 0.166097 -0.599979 -0.451032 </data>
</cnn_layers3_k00>
<cnn_layers3_k10 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.080095 -0.208276 0.109871 0.270457 0.783355 -0.260514 0.167258 1.011284 0.335274 0.107728 0.176377 1.066268 0.861674 0.399123 0.514124 1.209617 0.787085 0.194602 0.361981 0.960208 -0.479514 -0.878665 0.126446 0.075416 0.709474 </data>
</cnn_layers3_k10>
<cnn_layers3_k20 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.163346 0.202187 -0.140995 -0.240189 -0.619540 0.461728 0.217431 -0.724452 -0.663287 -0.136589 0.034402 -0.801644 -0.989194 -0.527616 -0.598525 -0.855531 -0.468462 -0.065309 -0.322047 -0.700459 -0.249037 1.273944 0.304968 -0.032917 -0.519410 </data>
</cnn_layers3_k20>
<cnn_layers3_k30 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.784990 1.167607 0.307104 -0.397623 -0.781330 0.902315 0.117752 -0.170410 -0.241356 -0.320337 -0.570828 -0.531624 -0.347680 -0.356497 -0.580216 -0.618820 -0.114257 0.071354 -0.073858 -0.692709 -0.124114 0.606057 0.278273 0.037596 -0.566463 </data>
</cnn_layers3_k30>
<cnn_layers3_k40 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.533587 0.738568 -0.067009 -0.034565 0.543938 -0.171653 -0.231780 0.156247 0.122206 -0.006857 -1.010811 0.165754 0.746727 0.185979 -0.196996 -0.023436 0.456139 0.342911 -0.029261 -0.191909 0.248712 -0.074521 -0.575833 -0.432815 -0.231696 </data>
</cnn_layers3_k40>
<cnn_layers3_k50 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.975987 0.782200 0.743849 0.094319 -0.494890 0.642745 0.706195 0.081159 -0.555033 -0.069618 1.123198 -0.273622 -0.798721 -0.783745 0.079391 -0.317877 -1.153055 -0.606408 -1.052097 -0.409909 -0.378006 0.299145 -0.417850 -0.956110 -0.478382 </data>
</cnn_layers3_k50>
<cnn_layers3_b0>-0.236482</cnn_layers3_b0>
<cnn_layers3_k01 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.926776 0.072317 0.004844 0.376807 0.271593 0.997414 0.899617 0.053917 0.282198 0.464503 0.655395 0.456988 -0.069831 0.466030 1.029693 0.781323 1.301913 1.865293 1.907672 0.616390 1.378092 1.397925 0.429482 0.104555 0.087357 </data>
</cnn_layers3_k01>
<cnn_layers3_k11 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.529301 0.050270 -0.259484 -0.256150 -0.085980 0.259601 -0.152911 0.024237 -0.334229 -0.073880 0.136170 -0.337684 -0.359674 -0.906475 0.057546 -0.552999 -1.781779 -1.598029 -0.741405 0.544478 -1.064832 0.183811 0.875609 0.699039 0.203665 </data>
</cnn_layers3_k11>
<cnn_layers3_k21 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.219132 0.222794 0.212542 -0.066117 -0.272729 0.030570 0.525351 -0.019025 -0.357542 -0.286049 0.070074 0.282191 0.662474 1.214310 0.443416 0.791089 1.874021 1.758268 1.348315 0.594553 1.430401 0.103339 -0.061522 -0.168939 0.348775 </data>
</cnn_layers3_k21>
<cnn_layers3_k31 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.665867 -0.486752 -0.481871 -0.174682 0.192365 -0.301444 -0.872443 -0.601543 -0.133027 0.041696 -0.638695 -0.528402 -0.142473 0.021412 0.626958 -0.303270 -1.074775 -0.315069 0.628346 0.388246 0.024993 -0.379166 -0.000361 -0.253064 -0.663144 </data>
</cnn_layers3_k31>
<cnn_layers3_k41 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.348724 1.543481 0.247467 -0.864648 -1.315569 0.373954 0.153263 -0.165562 -0.681692 -0.945003 0.538810 0.288737 -0.699918 -1.166144 -0.522463 -0.379773 -1.759357 -1.409138 -0.334280 -0.340475 -0.551458 -0.395234 0.478335 -0.058099 -0.183815 </data>
</cnn_layers3_k41>
<cnn_layers3_k51 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.113832 0.621539 -0.076790 -0.469457 -0.939045 0.416713 0.377521 -0.182465 -0.953154 -0.676424 0.300167 0.012660 -0.801795 0.015490 1.045571 -0.183411 0.399746 1.461250 1.562944 0.380658 0.344261 0.953795 -0.052846 -0.547063 -0.077568 </data>
</cnn_layers3_k51>
<cnn_layers3_b1>0.415523</cnn_layers3_b1>
<cnn_layers3_k02 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.442805 0.963578 0.679295 0.178223 -0.692602 -0.123565 0.794936 1.305936 0.563351 -0.323002 -0.280870 0.278230 0.463707 1.495047 0.593141 -0.563339 -0.222462 0.522316 0.729497 0.109938 -0.144214 -0.596058 -0.243113 0.197244 0.600164 </data>
</cnn_layers3_k02>
<cnn_layers3_k12 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.872999 -0.763303 -1.217161 -1.087039 0.149161 -0.501605 -1.097308 -1.196205 -0.752371 0.653330 -0.255119 -0.736578 -1.131551 -0.687080 0.832370 0.350346 0.300996 -1.111567 -0.628266 0.555587 0.017072 0.829746 0.032077 -0.506624 -0.383292 </data>
</cnn_layers3_k12>
<cnn_layers3_k22 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.587276 0.396350 0.426277 0.381113 -0.609158 0.313150 0.977445 0.816164 -0.029110 -0.765655 0.107369 0.555338 0.891674 0.746168 -0.269595 -0.280738 -0.720753 0.365065 0.740450 -0.383781 0.260286 -0.734946 -0.448088 -0.266900 -0.420117 </data>
</cnn_layers3_k22>
<cnn_layers3_k32 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.317127 -0.241607 -0.661255 -1.034351 -0.906838 0.919210 1.164235 -0.085525 -1.390807 -0.505167 -0.032780 0.084599 1.112131 -0.478688 0.134704 -0.562143 -0.809550 0.191064 -0.106200 -0.127577 -0.601251 -0.981574 -1.092511 -0.121306 -0.081121 </data>
</cnn_layers3_k32>
<cnn_layers3_k42 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.195347 -0.397792 0.418318 0.506091 0.820524 0.787673 -0.508089 -1.249163 -0.586654 1.109626 1.037333 0.465446 -1.048903 -1.543493 -0.308884 0.879707 0.294163 -0.517031 -1.362841 -0.661528 0.460142 0.408127 -0.282429 -0.629999 -0.330849 </data>
</cnn_layers3_k42>
<cnn_layers3_k52 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.162754 -0.228682 0.374115 0.257273 0.322096 -0.354268 -0.221165 0.160839 0.730326 0.951955 -0.269181 -0.706706 -0.813557 0.466257 0.950605 -0.302608 -0.858321 -0.816085 0.097629 0.487038 0.089978 -0.982404 -0.337495 -0.201452 0.581347 </data>
</cnn_layers3_k52>
<cnn_layers3_b2>0.058779</cnn_layers3_b2>
<cnn_layers3_k03 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.030865 -0.147504 -0.285091 -0.345849 -1.437360 0.418265 -0.271987 -0.275888 -0.336278 -0.738154 0.305927 -0.010533 -0.247946 -1.007451 -0.478779 0.384774 0.351528 -1.172181 -0.991227 0.185127 0.002921 0.467499 -1.090230 0.097062 0.197559 </data>
</cnn_layers3_k03>
<cnn_layers3_k13 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.369215 0.113866 0.022085 0.777760 0.296091 0.201666 0.110078 0.057470 0.714235 -0.453689 0.171296 -0.451586 0.533156 0.694475 -0.770069 -0.181319 -0.022842 1.172486 -0.428546 -0.355638 -0.163018 0.358330 0.167989 -0.898123 0.414345 </data>
</cnn_layers3_k13>
<cnn_layers3_k23 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.819600 -0.256654 -0.248564 -0.768261 -0.957816 0.635937 0.018570 -0.099577 -1.179124 -0.233931 0.116735 0.344817 -0.465593 -1.226703 0.173524 0.334882 0.173175 -1.685818 -0.311151 -0.092956 -0.133564 -0.303989 -1.384455 0.021121 -0.742201 </data>
</cnn_layers3_k23>
<cnn_layers3_k33 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.965256 0.256439 -0.036726 -1.587529 -0.560112 0.427691 0.060001 -0.603343 -1.334745 0.206705 0.471352 0.047862 -0.664035 -0.624298 0.479860 0.213308 -0.311779 -0.996167 -0.081255 -0.245720 -0.069599 -0.608494 -0.934784 0.144400 -0.631298 </data>
</cnn_layers3_k33>
<cnn_layers3_k43 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.419950 -0.028118 0.060380 0.379429 1.212201 -0.495534 0.506851 0.219246 0.656142 0.892528 -0.056298 0.041387 0.315354 1.098631 0.167733 0.139806 -0.555078 1.220091 0.563772 -0.106597 -0.098748 -0.379240 0.439459 0.364243 -0.057098 </data>
</cnn_layers3_k43>
<cnn_layers3_k53 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.280753 0.391900 0.376142 0.582076 -0.803885 0.320667 0.133955 0.566863 0.167615 -0.175051 0.057994 0.528303 0.988464 -0.762605 0.198912 -0.111439 1.053069 -0.123180 -0.189322 0.691036 -0.011225 0.720363 -0.410274 1.134817 -0.054976 </data>
</cnn_layers3_k53>
<cnn_layers3_b3>-0.127989</cnn_layers3_b3>
<cnn_layers3_k04 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.022546 -0.002744 0.306092 0.774629 0.625004 -0.490064 -0.693733 -0.311309 1.624117 0.642080 -0.271086 -0.392178 -0.340203 1.807729 0.564184 -0.149037 -0.002314 0.079090 1.588958 0.199407 -0.505103 0.085327 -0.479367 0.812799 0.867910 </data>
</cnn_layers3_k04>
<cnn_layers3_k14 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.137612 0.202028 -0.310713 -0.712972 0.256687 0.063299 0.586059 -0.243996 -1.138622 -0.574120 -0.751800 0.063244 -0.088624 -1.313318 -0.546560 -0.584075 -0.273935 -0.684995 -1.458527 -0.969534 -0.445028 -0.434559 0.146614 -1.567983 -1.890748 </data>
</cnn_layers3_k14>
<cnn_layers3_k24 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.187674 0.348623 0.633662 0.562573 -0.387165 -0.460669 -0.529179 -0.000553 0.987712 -0.419573 -0.005610 -0.920509 -0.446307 1.326085 -0.083407 0.272713 -0.318833 -0.081061 1.747997 0.620712 -0.134201 -0.341999 -0.239097 1.810688 1.732580 </data>
</cnn_layers3_k24>
<cnn_layers3_k34 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.329336 1.042262 1.308071 1.638232 1.117026 0.067335 -0.258786 0.716818 1.020568 -0.181668 -0.601301 -0.932378 0.771231 1.236248 0.889717 -0.335848 -0.473044 0.544403 0.890748 0.273198 -0.258299 -0.056007 0.740301 0.805761 0.204578 </data>
</cnn_layers3_k34>
<cnn_layers3_k44 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.477890 -0.894823 -0.865185 -0.819481 -1.060552 0.121316 0.201849 0.107148 -0.805983 -0.551632 0.302432 0.370971 0.522016 -0.752612 -0.672408 -0.205568 -0.208749 0.043301 -0.510446 -0.270926 -1.025185 -0.853891 0.292577 0.113995 -0.410339 </data>
</cnn_layers3_k44>
<cnn_layers3_k54 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.707929 -0.471537 -0.695229 1.084467 0.577385 -0.901033 -0.863422 -1.184878 0.934619 -0.217267 -0.427519 -0.499636 -0.930273 0.917007 -0.640424 -0.347681 -0.646758 -0.885003 0.823297 -0.901495 -1.552578 -1.325733 -1.110796 0.204505 -0.078499 </data>
</cnn_layers3_k54>
<cnn_layers3_b4>-0.493779</cnn_layers3_b4>
<cnn_layers3_k05 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.682665 0.508624 -0.000152 -0.739857 0.181171 0.125057 -0.228574 -0.739368 -1.237998 0.243818 0.135142 -0.155110 0.188995 -2.057010 0.196676 0.589670 0.109666 0.085411 -1.699831 0.194267 -0.265967 -0.067211 0.150488 -0.627716 -0.277764 </data>
</cnn_layers3_k05>
<cnn_layers3_k15 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.562465 -1.265863 0.049906 0.269077 0.595978 -0.012122 -1.104454 -0.238902 0.481171 -0.186345 -0.475397 -1.550673 -0.464135 1.155965 -0.269433 -0.413146 -1.216421 -0.422558 0.966497 0.010036 -0.190937 -0.652562 -0.114700 0.779470 0.155424 </data>
</cnn_layers3_k15>
<cnn_layers3_k25 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.482142 1.016055 -0.464672 -0.429979 -0.302332 0.205317 0.388807 -0.225252 -1.033340 0.385859 0.305382 0.817793 0.184567 -1.624715 0.221931 0.176411 0.420265 0.300382 -1.239470 0.258734 -0.065987 0.171707 0.127392 -1.466107 -0.653854 </data>
</cnn_layers3_k25>
<cnn_layers3_k35 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>1.093601 -0.238667 -1.768974 -0.519489 0.983662 1.137696 -0.192465 -1.203922 -0.702375 0.677581 0.703879 0.829253 -0.856541 -1.331064 0.308959 0.407042 0.977363 -0.208434 -1.368494 0.222778 0.078482 0.302207 -0.217767 -1.943461 -0.720938 </data>
</cnn_layers3_k35>
<cnn_layers3_k45 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.131742 -0.328539 -0.713259 0.453137 0.779356 -0.100959 -0.334826 -0.170064 0.558192 0.626338 0.266993 0.304039 -0.430964 0.949681 0.083174 0.243339 0.261912 -0.313837 1.006497 0.302147 0.947156 0.171888 -0.124524 0.306066 0.373813 </data>
</cnn_layers3_k45>
<cnn_layers3_k55 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.221595 0.236265 0.424545 -0.911560 0.837774 -0.230631 -0.436141 0.367240 -1.391301 0.617965 -0.354797 0.454628 0.862001 -1.087189 0.484881 0.328730 0.539817 0.770687 -0.613752 0.655114 0.257069 0.527997 1.147292 0.169299 0.112653 </data>
</cnn_layers3_k55>
<cnn_layers3_b5>0.072689</cnn_layers3_b5>
<cnn_layers3_k06 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-1.014982 -0.090826 0.016766 -0.852098 -0.405461 -0.577859 -0.487872 -1.006068 -0.117994 -0.012000 -1.261995 -1.635728 -0.484810 0.251251 0.121959 0.978287 0.258073 0.824503 0.849184 0.104913 0.990303 1.099688 1.033733 0.445782 0.091758 </data>
</cnn_layers3_k06>
<cnn_layers3_k16 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-1.007313 0.102937 0.665136 0.584373 0.614614 -0.309418 0.557140 0.669916 -0.007895 -0.117933 1.129587 1.239994 -0.217966 -0.696236 -0.164576 -0.362974 -0.971785 -0.145217 -0.114330 -0.099741 0.140309 0.078105 0.559419 0.466155 0.196720 </data>
</cnn_layers3_k16>
<cnn_layers3_k26 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.268387 -0.311324 -0.618581 -0.594792 -0.164316 -0.584853 -1.801164 -1.010384 -0.727189 0.201000 -1.006108 -1.538424 0.136957 0.133462 0.468382 0.821760 1.288794 0.756419 0.679262 0.250584 -0.089593 0.016427 -0.045062 -0.000048 -0.088301 </data>
</cnn_layers3_k26>
<cnn_layers3_k36 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.604900 -0.610622 -1.032363 -0.608456 -1.005701 -0.577829 -1.118030 -0.665332 -0.058547 0.339175 -1.102233 -0.595878 0.380659 0.952992 0.923465 0.130113 1.111791 0.900545 0.981266 -0.023202 1.354153 1.136773 -0.244229 -0.035996 -0.621583 </data>
</cnn_layers3_k36>
<cnn_layers3_k46 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>1.192172 -1.009474 -1.419040 0.276293 0.077375 0.218714 -0.344538 -0.127541 -0.051461 -0.009405 0.136037 0.872626 0.499446 0.052165 0.030108 -0.936959 -0.407917 -0.869936 -0.640386 -0.440722 -1.363014 -0.933223 -1.613415 0.055083 -0.041690 </data>
</cnn_layers3_k46>
<cnn_layers3_k56 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.584961 -0.198053 -0.078368 -0.481031 -0.425300 0.001749 -0.825886 -0.708438 -0.415013 0.431214 -0.438495 -1.210605 0.086126 0.833772 0.153948 0.121985 0.747306 0.914433 0.319247 -0.071577 0.200900 0.852254 0.343648 0.688435 -0.583900 </data>
</cnn_layers3_k56>
<cnn_layers3_b6>-0.269704</cnn_layers3_b6>
<cnn_layers3_k07 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.566660 -0.088470 0.322615 0.588513 -0.409033 -0.438380 -0.001259 1.527755 0.381399 -0.469921 0.480856 -0.121374 1.314365 -0.361530 -0.271370 0.983375 0.573636 0.339916 -0.312883 0.260235 0.545915 0.088019 -0.218662 -0.405615 -0.354188 </data>
</cnn_layers3_k07>
<cnn_layers3_k17 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.140547 0.312050 -0.688607 -0.864774 0.432897 0.176570 -0.320487 -1.464817 -0.359296 0.127227 0.064375 -0.935475 -0.824556 -0.064332 0.335488 -0.731266 -0.763866 0.030707 -0.459022 0.329490 -0.852177 -0.120440 0.184200 0.089403 1.103255 </data>
</cnn_layers3_k17>
<cnn_layers3_k27 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.519879 -0.994302 0.084052 0.626411 -0.286529 -0.395898 -0.624980 1.157890 0.182275 -0.039189 -0.113831 0.463209 0.727936 -0.792767 -0.106277 0.236161 0.365165 -0.164377 -0.399235 -0.385153 -0.083285 -0.672370 -1.289045 -0.992656 -1.351248 </data>
</cnn_layers3_k27>
<cnn_layers3_k37 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.128469 -0.517886 0.213635 0.404225 -0.220596 -0.422287 0.388133 0.719935 -0.331270 0.356643 0.270530 1.385065 -0.439969 -0.139707 0.737856 1.194628 0.600311 -1.036277 -0.183816 -0.330986 0.262279 -0.127261 -0.485602 -0.571428 -1.192310 </data>
</cnn_layers3_k37>
<cnn_layers3_k47 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.577187 0.077735 0.113271 -0.031007 0.496393 -0.248655 0.460476 -0.035146 -0.621240 -0.146091 0.018775 1.559222 -0.811910 -0.104578 -0.153962 0.208764 -0.591064 -0.886435 -0.027842 -0.430621 -0.339003 -0.426819 -0.448377 -0.739283 -0.589747 </data>
</cnn_layers3_k47>
<cnn_layers3_k57 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.308726 -0.201133 0.491224 0.643705 -1.140269 -0.734158 0.270566 1.347024 0.022561 -0.939263 0.169038 0.944050 0.858394 -0.860426 -0.273435 -0.107503 0.292655 0.023019 -0.664423 -0.187655 -0.294366 -0.198109 -0.798352 -0.753401 -1.061743 </data>
</cnn_layers3_k57>
<cnn_layers3_b7>-0.179914</cnn_layers3_b7>
<cnn_layers3_k08 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.668393 -0.862764 -0.605405 0.472296 1.080633 -0.784920 -0.496205 -0.790590 -0.396314 -0.111397 -1.438603 -0.967948 -0.639879 -0.141911 -0.550373 -0.729660 -1.093588 -1.141515 -0.140542 -0.249302 -0.448805 -0.407225 -0.495009 -0.377251 -0.241819 </data>
</cnn_layers3_k08>
<cnn_layers3_k18 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.811744 0.543894 0.181475 -0.140261 -0.371975 0.681886 0.473305 0.402477 0.530325 0.670544 1.535377 1.014083 0.182161 -0.060949 0.644101 1.592371 1.868465 1.105682 0.327601 0.465062 1.011275 0.967424 0.241614 0.140277 0.108958 </data>
</cnn_layers3_k18>
<cnn_layers3_k28 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.376322 -0.598659 -0.731610 -0.406680 0.533048 -0.347199 -0.174767 -0.407810 -0.470858 -0.297483 -1.112895 -0.525166 -0.602214 0.120981 0.086603 -0.591449 -0.990138 -1.126632 -0.294700 -0.077541 -0.104605 -0.320554 -0.313524 0.301268 0.562100 </data>
</cnn_layers3_k28>
<cnn_layers3_k38 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.097843 0.120007 0.589633 1.149928 1.914087 0.378823 0.222542 -0.577300 -0.590193 0.674750 -0.209986 -0.315688 -1.192901 -1.249628 0.184713 -0.721298 -0.596701 -1.177742 -0.974204 0.435103 -0.110788 -0.149641 -0.807758 -0.365623 0.787317 </data>
</cnn_layers3_k38>
<cnn_layers3_k48 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.674063 0.630285 1.065958 0.118419 0.061412 0.922700 1.184031 1.203945 0.252190 0.046849 0.801009 0.721328 0.177312 0.135344 0.428046 0.363680 0.692892 0.072010 0.202267 0.603411 0.049179 0.341542 -0.388278 0.332617 0.240752 </data>
</cnn_layers3_k48>
<cnn_layers3_k58 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.567821 -0.222831 0.469859 1.113208 1.236749 0.041129 0.390425 -0.217211 0.848202 0.344466 -0.097989 0.172888 0.008076 0.654781 -0.117653 -0.068884 0.122924 -0.206079 0.658807 0.281272 0.479292 0.024920 0.040282 0.624768 0.629352 </data>
</cnn_layers3_k58>
<cnn_layers3_b8>0.446793</cnn_layers3_b8>
<cnn_layers3_k09 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.676270 -0.607213 -0.982587 -0.063649 0.367744 -0.390845 -1.610829 -1.226808 -0.153300 0.162891 -0.556947 -1.706459 -0.840486 0.207216 0.128966 1.291363 -1.037691 -1.381526 0.324861 0.166920 0.453968 -0.063364 0.168568 0.356191 -0.045744 </data>
</cnn_layers3_k09>
<cnn_layers3_k19 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.060615 0.543545 0.795560 -0.547465 -0.473103 0.786105 0.949471 0.611570 -0.176119 -0.638894 0.112526 0.966945 0.423135 -0.635346 -0.579076 -0.586954 0.706106 0.509453 -0.925902 -0.075283 -0.583107 -0.396572 -0.258973 -0.460995 -0.328232 </data>
</cnn_layers3_k19>
<cnn_layers3_k29 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.365860 -0.552002 -0.452940 0.012814 0.257564 -0.813635 -1.596153 -1.095164 -0.670859 0.088780 0.197788 -1.305068 -1.042413 0.157810 0.497732 0.978197 -0.881694 -0.656067 0.618500 -0.136148 0.912997 0.651954 0.052847 -0.550045 -0.047963 </data>
</cnn_layers3_k29>
<cnn_layers3_k39 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.592027 -0.329896 -0.034928 0.868870 0.192741 0.294601 -0.682302 -0.539165 0.142024 0.802247 0.546344 -0.737097 -0.960936 0.464528 0.818215 0.367924 -1.190235 -0.132229 1.009130 0.031181 0.979928 -0.626317 -0.865374 -0.335967 0.319851 </data>
</cnn_layers3_k39>
<cnn_layers3_k49 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.998391 -0.353279 -0.065516 -0.233267 -0.942785 0.069688 0.813087 0.294335 0.091451 -0.492721 -0.261148 -0.420685 0.108469 0.212320 0.286216 -1.247263 0.096445 1.231619 0.767045 -0.120550 -1.002968 -0.233698 0.293052 0.630827 -0.278709 </data>
</cnn_layers3_k49>
<cnn_layers3_k59 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>1.246215 0.821898 0.269541 0.856366 0.595405 0.295491 -0.664558 -0.463526 -0.054531 0.312528 0.088134 -0.706600 -0.210633 0.972126 0.824191 1.224268 0.535979 -0.026173 1.632863 0.394902 0.660313 1.232343 1.490387 1.358453 0.545385 </data>
</cnn_layers3_k59>
<cnn_layers3_b9>-0.359446</cnn_layers3_b9>
<cnn_layers3_k010 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-1.546003 -0.187323 0.105723 -0.018114 1.095362 -0.759533 -0.559511 0.034126 0.891905 1.070529 -0.200035 -1.155163 0.408871 0.859702 0.125615 -0.704433 -0.945886 0.727630 -0.136279 0.518782 -1.070746 -0.348453 0.228575 -0.687764 -0.032269 </data>
</cnn_layers3_k010>
<cnn_layers3_k110 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.026630 0.400576 0.952556 0.245570 -0.463552 0.039035 1.155123 -0.609885 -0.148316 1.078307 0.318322 0.511580 -1.379081 0.256026 0.271267 0.759982 -0.654717 -0.461534 0.367066 -0.178345 -0.447060 -0.776722 0.432413 -0.508136 -0.208986 </data>
</cnn_layers3_k110>
<cnn_layers3_k210 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.653463 -0.994536 -1.103004 -0.129484 1.637813 -0.486291 -1.084926 -0.108438 1.116738 0.410824 -0.279628 -0.739515 1.848043 0.912253 0.290845 -0.294105 0.733837 1.123886 0.067098 0.432019 -0.534730 1.064048 -0.719221 0.085087 0.261381 </data>
</cnn_layers3_k210>
<cnn_layers3_k310 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-1.247153 -1.405349 -1.515371 -0.040739 1.663579 -1.628287 -1.620912 0.136292 1.234565 0.550759 -0.795693 0.400257 0.989605 -0.096351 0.071876 0.918387 1.256296 -0.254218 -0.178121 0.557086 0.415385 0.903988 -0.388354 0.066811 0.464434 </data>
</cnn_layers3_k310>
<cnn_layers3_k410 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.668101 -0.603855 -0.927092 -0.313260 -0.081728 -0.556550 -0.529253 -0.577946 -1.051073 -1.096032 -0.385259 0.649552 -0.432952 -0.830818 -0.202165 0.747385 -0.088106 -0.792758 0.098937 -0.144375 0.752500 -0.345553 -0.268536 -0.037663 0.100931 </data>
</cnn_layers3_k410>
<cnn_layers3_k510 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.819646 -0.061544 -0.621528 -0.116210 1.640329 -1.241785 -1.391293 -0.322537 1.009440 -0.097069 0.021287 -1.299652 0.565523 0.787587 -0.514825 -0.356127 -0.374071 1.519979 0.168198 -0.053134 -0.576439 1.862486 0.093492 0.475723 -0.281079 </data>
</cnn_layers3_k510>
<cnn_layers3_b10>-0.335266</cnn_layers3_b10>
<cnn_layers3_k011 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.505077 0.072460 0.794927 1.257610 -0.490060 0.414314 -0.349773 1.827751 0.819248 -0.323527 -0.556424 -0.597079 1.872513 0.466398 -0.281778 -0.772734 0.103448 1.657354 0.070528 0.630711 -0.347049 0.461002 0.322763 -0.136470 1.082132 </data>
</cnn_layers3_k011>
<cnn_layers3_k111 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.039265 -0.273131 -0.715524 0.322679 0.280288 0.488535 0.093693 -1.514492 0.892310 0.123340 1.284891 0.855584 -0.982190 0.918577 0.290553 0.953731 -0.092180 -0.037669 0.500257 0.339102 0.328115 -0.140655 1.037077 0.139284 -0.079438 </data>
</cnn_layers3_k111>
<cnn_layers3_k211 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.019645 -0.242623 0.275504 -0.561037 -0.253620 0.052918 -0.652420 1.454981 -0.583989 -0.418579 -0.582240 -1.255313 1.743450 -0.928743 -0.075638 -0.788392 0.178144 0.667918 -0.355271 0.420243 0.006391 1.270100 -0.399300 -0.279128 0.591912 </data>
</cnn_layers3_k211>
<cnn_layers3_k311 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>0.206344 -0.137793 0.441569 -1.695329 -1.533246 -0.832548 -0.078969 1.188865 -0.975308 -1.190569 -1.518431 -0.147745 0.108640 -1.739391 -0.516873 -1.207976 -0.436199 -1.426958 -0.687373 0.248862 -0.022596 -1.307910 -1.000817 0.105068 0.034526 </data>
</cnn_layers3_k311>
<cnn_layers3_k411 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.471366 -0.275459 -0.114313 -0.475209 1.448534 -0.371305 0.568451 -0.474636 -0.644216 0.174488 0.590902 0.972793 -1.749462 -0.974484 0.036854 0.915704 0.907947 -2.375169 -0.015095 -0.053157 1.572970 -0.543742 -0.802352 -0.049666 0.288547 </data>
</cnn_layers3_k411>
<cnn_layers3_k511 type_id="opencv-matrix">
<rows>5</rows>
<cols>5</cols>
<dt>f</dt>
<data>-0.612179 -0.590088 0.782748 0.324497 -1.535196 -0.400298 -0.771880 1.329301 -0.126572 -0.991845 -0.488720 -0.102490 0.739774 -0.407288 0.056013 -0.309510 0.481685 0.740026 -0.516061 0.513591 0.044610 0.584247 0.367993 -0.255021 0.828662 </data>
</cnn_layers3_k511>
<cnn_layers3_b11>0.645863</cnn_layers3_b11>
<cnn_layers4_type>115</cnn_layers4_type>
<cnn_layers4_scale>2</cnn_layers4_scale>
<test_data type_id="opencv-matrix">
<rows>28</rows>
<cols>28</cols>
<dt>f</dt>
<data>0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.203922<