/*
k-means center initialization using the following algorithm:
Arthur & Vassilvitskii (2007) k-means++: The Advantages of Careful Seeding
*/
static void generateCentersPP(const Mat& _data, Mat& _out_centers,
int K, RNG& rng, int trials)
{
int i, j, k, dims = _data.cols, N = _data.rows;
const float* data = _data.ptr<float>(0);
size_t step = _data.step/sizeof(data[0]);
std::vector<int> _centers(K);
int* centers = &_centers[0];
std::vector<float> _dist(N*3);
float* dist = &_dist[0], *tdist = dist + N, *tdist2 = tdist + N;
double sum0 = 0;
centers[0] = (unsigned)rng % N;
for( i = 0; i < N; i++ )
{
dist[i] = normL2Sqr(data + step*i, data + step*centers[0], dims);
sum0 += dist[i];
}
for( k = 1; k < K; k++ )
{
double bestSum = DBL_MAX;
int bestCenter = -1;
for( j = 0; j < trials; j++ )
{
double p = (double)rng*sum0, s = 0;
for( i = 0; i < N-1; i++ )
if( (p -= dist[i]) <= 0 )
break;
int ci = i;
parallel_for_(Range(0, N),
KMeansPPDistanceComputer(tdist2, data, dist, dims, step, step*ci));
for( i = 0; i < N; i++ )
{
s += tdist2[i];
}
if( s < bestSum )
{
bestSum = s;
bestCenter = ci;
std::swap(tdist, tdist2);
}
}
centers[k] = bestCenter;
sum0 = bestSum;
std::swap(dist, tdist);
}
for( k = 0; k < K; k++ )
{
const float* src = data + step*centers[k];
float* dst = _out_centers.ptr<float>(k);
for( j = 0; j < dims; j++ )
dst[j] = src[j];
}
}
void HistEncoding::deserializeSpec(const tinyxml2::XMLElement* root)
{
if (const tinyxml2::XMLElement *k = root->FirstChildElement("k"))
{
k->QueryIntText(&_k);
}
if (const tinyxml2::XMLElement *pca = root->FirstChildElement("pca"))
{
_usePCA = true;
pca->QueryIntText(&_pcaDim);
}
if (const tinyxml2::XMLElement *centers = root->FirstChildElement("centers"))
{
_computed = true;
const tinyxml2::XMLElement *center = centers->FirstChildElement("center");
std::vector<std::string> elems = stringSplit(std::string(center->GetText()), ' ');
_centers = SampleType(_k, elems.size());
std::cout << elems.size() << std::endl;
int row = 0;
for (size_t i = 0; i < elems.size(); ++i)
{
_centers(row, i) = boost::lexical_cast<Scalar>(elems[i]);
}
row = 1;
for (center = center->NextSiblingElement("center");
center != NULL;
center = center->NextSiblingElement("center"))
{
elems = stringSplit(std::string(center->GetText()), ' ');
for (unsigned int i = 0; i < _centers.cols(); ++i)
{
_centers(row, i) = boost::lexical_cast<Scalar>(elems[i]);
}
row += 1;
}
_tree = new tet::classification::util::ANNTree<Scalar>(_centers);
}
}
