| 1 |
//########################################################################## |
| 2 |
//# # |
| 3 |
//# CLOUDCOMPARE PLUGIN: qCANUPO # |
| 4 |
//# # |
| 5 |
//# This program is free software; you can redistribute it and/or modify # |
| 6 |
//# it under the terms of the GNU General Public License as published by # |
| 7 |
//# the Free Software Foundation; version 2 or later of the License. # |
| 8 |
//# # |
| 9 |
//# This program is distributed in the hope that it will be useful, # |
| 10 |
//# but WITHOUT ANY WARRANTY; without even the implied warranty of # |
| 11 |
//# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # |
| 12 |
//# GNU General Public License for more details. # |
| 13 |
//# # |
| 14 |
//# COPYRIGHT: UEB (UNIVERSITE EUROPEENNE DE BRETAGNE) / CNRS # |
| 15 |
//# # |
| 16 |
//########################################################################## |
| 17 |
|
| 18 |
/** This file is directly inspired of the suggest_classifier_lda.cpp file in the |
| 19 |
original CANUPO project, by N. Brodu and D. Lague. |
| 20 |
**/ |
| 21 |
|
| 22 |
#ifndef QCANUPO_TRAINER_HEADER |
| 23 |
#define QCANUPO_TRAINER_HEADER |
| 24 |
|
| 25 |
//system |
| 26 |
#include <vector> |
| 27 |
|
| 28 |
//dlib |
| 29 |
#include <dlib/matrix.h> |
| 30 |
#include <dlib/svm.h> |
| 31 |
|
| 32 |
class LDATrainer |
| 33 |
{ |
| 34 |
public: |
| 35 |
|
| 36 |
typedef dlib::matrix<float, 0, 1> sample_type; |
| 37 |
typedef dlib::linear_kernel<sample_type> kernel_type; |
| 38 |
typedef dlib::decision_function<kernel_type> trained_function_type; |
| 39 |
//typedef trained_function_type::mem_manager_type mem_manager_type; |
| 40 |
|
| 41 |
trained_function_type train(const std::vector<sample_type>& samplesvec, const std::vector<float>& labels) const |
| 42 |
{ |
| 43 |
size_t fdim = samplesvec[0].size(); |
| 44 |
size_t nsamples = samplesvec.size(); |
| 45 |
|
| 46 |
long ndata_class1 = 0, ndata_class2 = 0; |
| 47 |
for (size_t i = 0; i < nsamples; ++i) |
| 48 |
{ |
| 49 |
if (labels[i] > 0) |
| 50 |
++ndata_class1; |
| 51 |
else |
| 52 |
++ndata_class2; |
| 53 |
} |
| 54 |
|
| 55 |
dlib::matrix<sample_type, 0, 1> samples1, samples2; |
| 56 |
samples1.set_size(ndata_class1); |
| 57 |
samples2.set_size(ndata_class2); |
| 58 |
sample_type mu1; mu1.set_size(fdim); |
| 59 |
sample_type mu2; mu2.set_size(fdim); |
| 60 |
for (size_t i = 0; i < fdim; ++i) |
| 61 |
{ |
| 62 |
mu1(i) = 0; |
| 63 |
mu2(i) = 0; |
| 64 |
} |
| 65 |
|
| 66 |
ndata_class1 = 0; ndata_class2 = 0; |
| 67 |
for (size_t i = 0; i < nsamples; ++i) |
| 68 |
{ |
| 69 |
if (labels[i] > 0) |
| 70 |
{ |
| 71 |
samples1(ndata_class1) = samplesvec[i]; |
| 72 |
++ndata_class1; |
| 73 |
mu1 += samplesvec[i]; |
| 74 |
} |
| 75 |
else |
| 76 |
{ |
| 77 |
samples2(ndata_class2) = samplesvec[i]; |
| 78 |
++ndata_class2; |
| 79 |
mu2 += samplesvec[i]; |
| 80 |
} |
| 81 |
} |
| 82 |
if (ndata_class1 != 0) |
| 83 |
{ |
| 84 |
mu1 /= ndata_class1; |
| 85 |
} |
| 86 |
if (ndata_class2 != 0) |
| 87 |
{ |
| 88 |
mu2 /= ndata_class2; |
| 89 |
} |
| 90 |
|
| 91 |
// if you get a compilation error coming from here (with templates |
| 92 |
// and a 'visual_studio_sucks_cov_helper' structure involved) then |
| 93 |
// you may have to patch the dlib's file 'matrix_utilities.h": |
| 94 |
// |
| 95 |
// line 1611, replace |
| 96 |
// const matrix<double,EXP::type::NR,EXP::type::NC, typename EXP::mem_manager_type> avg = mean(m); |
| 97 |
// by |
| 98 |
// const typename EXP::type avg = mean(m); |
| 99 |
// |
| 100 |
dlib::matrix<float> sigma1 = covariance(samples1); |
| 101 |
dlib::matrix<float> sigma2 = covariance(samples2); |
| 102 |
|
| 103 |
sample_type w_vect = pinv(sigma1 + sigma2) * (mu2 - mu1); |
| 104 |
|
| 105 |
trained_function_type ret; |
| 106 |
//ret.alpha.set_size(fdim); |
| 107 |
//for (int i=0; i<fdim; ++i) ret.alpha(i) = w_vect(i); |
| 108 |
ret.alpha = w_vect; |
| 109 |
ret.b = dot(w_vect, (mu1 + mu2)*0.5); |
| 110 |
// linear kernel idiocy |
| 111 |
ret.basis_vectors.set_size(fdim); |
| 112 |
for (size_t i = 0; i < fdim; ++i) |
| 113 |
{ |
| 114 |
ret.basis_vectors(i).set_size(fdim); |
| 115 |
for (size_t j = 0; j < fdim; ++j) |
| 116 |
ret.basis_vectors(i)(j) = 0; |
| 117 |
ret.basis_vectors(i)(i) = 1; |
| 118 |
} |
| 119 |
return ret; |
| 120 |
} |
| 121 |
|
| 122 |
#if 0 |
| 123 |
trained_function_type train(const trained_function_type::sample_vector_type& samplesvec, const trained_function_type::scalar_vector_type& labels) const |
| 124 |
{ |
| 125 |
int fdim = samplesvec(0).size(); |
| 126 |
int nsamples = samplesvec.size(); |
| 127 |
|
| 128 |
int ndata_class1 = 0, ndata_class2 = 0; |
| 129 |
for (int i=0; i<nsamples; ++i) |
| 130 |
{ |
| 131 |
if (labels(i)>0) |
| 132 |
++ndata_class1; |
| 133 |
else |
| 134 |
++ndata_class2; |
| 135 |
} |
| 136 |
|
| 137 |
dlib::matrix<sample_type,0,1> samples1, samples2; |
| 138 |
samples1.set_size(ndata_class1); |
| 139 |
samples2.set_size(ndata_class2); |
| 140 |
sample_type mu1; mu1.set_size(fdim); |
| 141 |
sample_type mu2; mu2.set_size(fdim); |
| 142 |
for (int i=0; i<fdim; ++i) |
| 143 |
{ |
| 144 |
mu1(i)=0; |
| 145 |
mu2(i)=0; |
| 146 |
} |
| 147 |
|
| 148 |
ndata_class1 = 0; ndata_class2 = 0; |
| 149 |
for (int i=0; i<nsamples; ++i) |
| 150 |
{ |
| 151 |
if (labels(i)>0) |
| 152 |
{ |
| 153 |
samples1(ndata_class1) = samplesvec(i); |
| 154 |
++ndata_class1; |
| 155 |
mu1 += samplesvec(i); |
| 156 |
} |
| 157 |
else |
| 158 |
{ |
| 159 |
samples2(ndata_class2) = samplesvec(i); |
| 160 |
++ndata_class2; |
| 161 |
mu2 += samplesvec(i); |
| 162 |
} |
| 163 |
} |
| 164 |
mu1 /= ndata_class1; |
| 165 |
mu2 /= ndata_class2; |
| 166 |
|
| 167 |
// if you get a compilation error coming from here (with templates |
| 168 |
// and a 'visual_studio_sucks_cov_helper' structure involved) then |
| 169 |
// you may have to patch the dlib's file 'matrix_utilities.h": |
| 170 |
// |
| 171 |
// line 1611, replace |
| 172 |
// const matrix<double,EXP::type::NR,EXP::type::NC, typename EXP::mem_manager_type> avg = mean(m); |
| 173 |
// by |
| 174 |
// const typename EXP::type avg = mean(m); |
| 175 |
// |
| 176 |
dlib::matrix<float> sigma1 = covariance(samples1); |
| 177 |
dlib::matrix<float> sigma2 = covariance(samples2); |
| 178 |
|
| 179 |
sample_type w_vect = pinv(sigma1+sigma2) * (mu2 - mu1); |
| 180 |
|
| 181 |
trained_function_type ret; |
| 182 |
//ret.alpha.set_size(fdim); |
| 183 |
//for (int i=0; i<fdim; ++i) ret.alpha(i) = w_vect(i); |
| 184 |
ret.alpha = w_vect; |
| 185 |
ret.b = dot(w_vect,(mu1+mu2)*0.5); |
| 186 |
// linear kernel idiocy |
| 187 |
ret.basis_vectors.set_size(fdim); |
| 188 |
for (int i=0; i<fdim; ++i) |
| 189 |
{ |
| 190 |
ret.basis_vectors(i).set_size(fdim); |
| 191 |
for (int j=0; j<fdim; ++j) |
| 192 |
ret.basis_vectors(i)(j)=0; |
| 193 |
ret.basis_vectors(i)(i) = 1; |
| 194 |
} |
| 195 |
return ret; |
| 196 |
/*LinearPredictor classifier; |
| 197 |
classifier.weights.resize(fdim+1); |
| 198 |
for (int i=0; i<fdim; ++i) classifier.weights[i] = w_vect(i); |
| 199 |
classifier.weights[fdim] = -dot(w_vect,(mu1+mu2)*0.5); |
| 200 |
return classifier;*/ |
| 201 |
} |
| 202 |
#endif |
| 203 |
|
| 204 |
void train(int nfolds, const std::vector<sample_type>& samples, const std::vector<float>& labels) |
| 205 |
{ |
| 206 |
dlib::probabilistic_decision_function<kernel_type> pdecfun = dlib::train_probabilistic_decision_function(*this, samples, labels, nfolds); |
| 207 |
dlib::decision_function<kernel_type>& decfun = pdecfun.decision_funct; |
| 208 |
int dim = samples.back().size(); |
| 209 |
// see comments in linearSVM.hpp |
| 210 |
m_weights.clear(); |
| 211 |
m_weights.resize(dim + 1, 0); |
| 212 |
dlib::matrix<float> w(dim, 1); |
| 213 |
w = 0; |
| 214 |
for (int i = 0; i < decfun.alpha.nr(); ++i) |
| 215 |
{ |
| 216 |
w += decfun.alpha(i) * decfun.basis_vectors(i); |
| 217 |
} |
| 218 |
for (int i = 0; i < dim; ++i) |
| 219 |
m_weights[i] = w(i); |
| 220 |
m_weights[dim] = -decfun.b; |
| 221 |
for (int i = 0; i <= dim; ++i) |
| 222 |
m_weights[i] *= pdecfun.alpha; |
| 223 |
m_weights[dim] += pdecfun.beta; |
| 224 |
|
| 225 |
// TODO: check if necessary here |
| 226 |
for (int i = 0; i <= dim; ++i) |
| 227 |
m_weights[i] = -m_weights[i]; |
| 228 |
} |
| 229 |
|
| 230 |
double predict(const sample_type& data) const |
| 231 |
{ |
| 232 |
assert(!m_weights.empty()); |
| 233 |
double ret = m_weights.back(); |
| 234 |
for (size_t d = 0; d < m_weights.size() - 1; ++d) |
| 235 |
ret += static_cast<double>(m_weights[d]) * data(d); |
| 236 |
return ret; |
| 237 |
} |
| 238 |
|
| 239 |
//! Classifier weights |
| 240 |
std::vector<float> m_weights; |
| 241 |
|
| 242 |
}; |
| 243 |
|
| 244 |
//! Gram-Schmidt process to re-orthonormalise the basis |
| 245 |
static void GramSchmidt(dlib::matrix<LDATrainer::sample_type,0,1>& basis, LDATrainer::sample_type& newX) |
| 246 |
{ |
| 247 |
// goal: find a basis so that the given vector is the new X |
| 248 |
// principle: at least one basis vector is not orthogonal with newX (except if newX is null but we suppose this is not the case) |
| 249 |
// => use the max dot product vector, and replace it by newX. this forms a set of |
| 250 |
// linearly independent vectors. |
| 251 |
// then apply the Gram-Schmidt process |
| 252 |
long dim = basis.size(); |
| 253 |
double maxabsdp = -1.0; |
| 254 |
long selectedCoord = 0; |
| 255 |
for (long i = 0; i < dim; ++i) |
| 256 |
{ |
| 257 |
double absdp = std::abs(dot(basis(i), newX)); |
| 258 |
if (absdp > maxabsdp) |
| 259 |
{ |
| 260 |
absdp = maxabsdp; |
| 261 |
selectedCoord = i; |
| 262 |
} |
| 263 |
} |
| 264 |
// swap basis vectors to use the selected coord as the X vector, then replaced by newX |
| 265 |
basis(selectedCoord) = basis(0); |
| 266 |
basis(0) = newX; |
| 267 |
// Gram-Schmidt process to re-orthonormalise the basis. |
| 268 |
// Thanks Wikipedia for the stabilized version |
| 269 |
for (long j = 0; j < dim; ++j) |
| 270 |
{ |
| 271 |
for (long i = 0; i < j; ++i) |
| 272 |
basis(j) -= (dot(basis(j), basis(i)) / dot(basis(i), basis(i))) * basis(i); |
| 273 |
|
| 274 |
basis(j) /= sqrt(dot(basis(j), basis(j))); |
| 275 |
} |
| 276 |
} |
| 277 |
|
| 278 |
//! Compute pos. and neg. reference points |
| 279 |
static void ComputeReferencePoints( Classifier::Point2D& refpt_pos, |
| 280 |
Classifier::Point2D& refpt_neg, |
| 281 |
const std::vector<float>& proj1, |
| 282 |
const std::vector<float>& proj2, |
| 283 |
const std::vector<float>& labels, |
| 284 |
unsigned* _npos = 0, |
| 285 |
unsigned* _nneg = 0) |
| 286 |
{ |
| 287 |
assert(proj1.size() == proj2.size() && proj1.size() == labels.size()); |
| 288 |
|
| 289 |
refpt_neg = refpt_pos = Classifier::Point2D(0, 0); |
| 290 |
|
| 291 |
size_t npos = 0; |
| 292 |
size_t nneg = 0; |
| 293 |
for (size_t i = 0; i < labels.size(); ++i) |
| 294 |
{ |
| 295 |
if (labels[i] < 0) |
| 296 |
{ |
| 297 |
refpt_neg += Classifier::Point2D(proj1[i], proj2[i]); |
| 298 |
++nneg; |
| 299 |
} |
| 300 |
else |
| 301 |
{ |
| 302 |
refpt_pos += Classifier::Point2D(proj1[i], proj2[i]); |
| 303 |
++npos; |
| 304 |
} |
| 305 |
} |
| 306 |
if (npos) |
| 307 |
refpt_pos /= static_cast<PointCoordinateType>(npos); |
| 308 |
if (nneg) |
| 309 |
refpt_neg /= static_cast<PointCoordinateType>(nneg); |
| 310 |
|
| 311 |
if (_npos) |
| 312 |
*_npos = npos; |
| 313 |
if (_nneg) |
| 314 |
*_nneg = nneg; |
| 315 |
} |
| 316 |
|
| 317 |
//! Experimental (same as Brodu's code): dilatation to highlight the internal data structure |
| 318 |
static bool DilateClassifier( Classifier& classifier, |
| 319 |
std::vector<float>& proj1, |
| 320 |
std::vector<float>& proj2, |
| 321 |
const std::vector<float>& labels, |
| 322 |
const std::vector<LDATrainer::sample_type>& samples, |
| 323 |
LDATrainer& trainer, |
| 324 |
LDATrainer& orthoTrainer) |
| 325 |
{ |
| 326 |
//m_app->dispToConsole("[Cloud dilatation]"); |
| 327 |
Classifier::Point2D e1 = classifier.refPointPos - classifier.refPointNeg; |
| 328 |
e1.normalize(); |
| 329 |
Classifier::Point2D e2(-e1.y, e1.x); |
| 330 |
Classifier::Point2D ori = (classifier.refPointPos + classifier.refPointNeg) / 2; |
| 331 |
|
| 332 |
float m11 = 0, m21 = 0, m12 = 0, m22 = 0; // m12, m22 null by construction |
| 333 |
float v11 = 0, v12 = 0, v21 = 0, v22 = 0; |
| 334 |
size_t nsamples1 = 0; |
| 335 |
size_t nsamples2 = 0; |
| 336 |
size_t nsamples = proj1.size(); |
| 337 |
assert(proj1.size() == proj2.size()); |
| 338 |
for (size_t i = 0; i < nsamples; ++i) |
| 339 |
{ |
| 340 |
Classifier::Point2D p(proj1[i], proj2[i]); |
| 341 |
p -= ori; |
| 342 |
float p1 = p.dot(e1); |
| 343 |
float p2 = p.dot(e2); |
| 344 |
if (labels[i] < 0) |
| 345 |
{ |
| 346 |
m11 += p1; v11 += p1 * p1; |
| 347 |
m12 += p2; v12 += p2 * p2; |
| 348 |
++nsamples1; |
| 349 |
} |
| 350 |
else |
| 351 |
{ |
| 352 |
m21 += p1; v21 += p1 * p1; |
| 353 |
m22 += p2; v22 += p2 * p2; |
| 354 |
++nsamples2; |
| 355 |
} |
| 356 |
} |
| 357 |
|
| 358 |
if (nsamples1 < 2 || nsamples2 < 2) |
| 359 |
{ |
| 360 |
assert(false); |
| 361 |
return false; |
| 362 |
} |
| 363 |
|
| 364 |
m11 /= nsamples1; |
| 365 |
v11 = (v11 - m11 * m11*nsamples1) / (nsamples1 - 1); |
| 366 |
m21 /= nsamples2; |
| 367 |
v21 = (v21 - m21 * m21*nsamples2) / (nsamples2 - 1); |
| 368 |
m12 /= nsamples1; |
| 369 |
v12 = (v12 - m12 * m12*nsamples1) / (nsamples1 - 1); |
| 370 |
m22 /= nsamples2; |
| 371 |
v22 = (v22 - m22 * m22*nsamples2) / (nsamples2 - 1); |
| 372 |
|
| 373 |
float d1 = sqrt(v11 / v12); |
| 374 |
float d2 = sqrt(v21 / v22); |
| 375 |
classifier.axisScaleRatio = sqrt(d1*d2); |
| 376 |
|
| 377 |
float bdValues[4] { e1.x, e1.y, e2.x / classifier.axisScaleRatio, e2.y / classifier.axisScaleRatio }; |
| 378 |
dlib::matrix<float, 2, 2> bd(bdValues); |
| 379 |
|
| 380 |
float biValues[4] { e1.x, e2.x, e1.y, e2.y }; |
| 381 |
dlib::matrix<float, 2, 2> bi(biValues); |
| 382 |
dlib::matrix<float, 2, 2> c = inv(trans(bd)) /* bi * bd */; |
| 383 |
|
| 384 |
std::vector<float>& w1 = trainer.m_weights; |
| 385 |
std::vector<float>& w2 = orthoTrainer.m_weights; |
| 386 |
assert(w1.size() == w2.size()); |
| 387 |
|
| 388 |
std::vector<float> wn1, wn2; |
| 389 |
try |
| 390 |
{ |
| 391 |
wn1.resize(w1.size()); |
| 392 |
wn2.resize(w2.size()); |
| 393 |
} |
| 394 |
catch (const std::bad_alloc&) |
| 395 |
{ |
| 396 |
//not enough memory |
| 397 |
return false; |
| 398 |
} |
| 399 |
|
| 400 |
// first shift so the center of the figure is at the midpoint |
| 401 |
w1.back() -= ori.x; |
| 402 |
w2.back() -= ori.y; |
| 403 |
// now transform / scale along e2 |
| 404 |
{ |
| 405 |
for (size_t i = 0; i < w1.size(); ++i) |
| 406 |
{ |
| 407 |
wn1[i] = c(0, 0) * w1[i] + c(0, 1) * w2[i]; |
| 408 |
wn2[i] = c(1, 0) * w1[i] + c(1, 1) * w2[i]; |
| 409 |
} |
| 410 |
} |
| 411 |
|
| 412 |
trainer.m_weights = wn1; |
| 413 |
orthoTrainer.m_weights = wn2; |
| 414 |
|
| 415 |
// reset projections |
| 416 |
{ |
| 417 |
for (size_t i = 0; i < nsamples; ++i) |
| 418 |
{ |
| 419 |
proj1[i] = trainer.predict(samples[i]); |
| 420 |
proj2[i] = orthoTrainer.predict(samples[i]); |
| 421 |
} |
| 422 |
} |
| 423 |
|
| 424 |
classifier.weightsAxis1 = wn1; |
| 425 |
classifier.weightsAxis2 = wn2; |
| 426 |
|
| 427 |
//update reference points |
| 428 |
ComputeReferencePoints( classifier.refPointPos, |
| 429 |
classifier.refPointNeg, |
| 430 |
proj1, |
| 431 |
proj2, |
| 432 |
labels); |
| 433 |
|
| 434 |
return true; |
| 435 |
} |
| 436 |
|
| 437 |
#endif //QCANUPO_CLASSIFIER_HEADER |