void kmeans()
{
const vl_size data_dim = 2;
const vl_size num_data = 1000;
float data[data_dim * num_data] = { 0.0f, };
for (vl_size i = 0; i < data_dim * num_data; ++i)
data[i] = (float)std::rand() / RAND_MAX;
//
std::cout << "start processing ..." << std::endl;
const vl_size num_clusters = 3;
const VlVectorComparisonType distance = VlDistanceL2;
const vl_size num_max_iterations = 100;
VlKMeans *kmeans = vl_kmeans_new(VL_TYPE_DOUBLE, distance);
vl_kmeans_set_max_num_iterations(kmeans, num_max_iterations);
if (true)
{
// initialization.
#if 1
vl_kmeans_init_centers_with_rand_data(kmeans, (void const *)data, data_dim, num_data, num_clusters);
#elif 0
vl_kmeans_init_centers_plus_plus(kmeans, (void const *)data, data_dim, num_data, num_clusters);
#else
{
float init_centers[data_dim * num_clusters] = { 0.0f, };
for (vl_size i = 0; i < data_dim * num_clusters; ++i)
init_centers[i] = (float)std::rand() / RAND_MAX;
vl_kmeans_set_centers(kmeans, (void const *)init_centers, data_dim, num_clusters);
}
#endif
// clustering.
const double energy = vl_kmeans_refine_centers(kmeans, data, num_data);
}
else
{
const VlKMeansAlgorithm algorithm = VlKMeansLloyd; // VlKMeansLloyd, VlKMeansElkan, VlKMeansANN.
const VlKMeansInitialization initialization = VlKMeansRandomSelection; // VlKMeansRandomSelection, VlKMeansPlusPlus.
const vl_size num_repetitions = 100;
vl_kmeans_set_algorithm(kmeans, VlKMeansLloyd);
vl_kmeans_set_initialization(kmeans, VlKMeansRandomSelection);
vl_kmeans_set_num_repetitions(kmeans, num_repetitions);
// clustering.
const double energy = vl_kmeans_cluster(kmeans, (void const *)data, data_dim, num_data, num_clusters);
}
//
const vl_size num_iterations = vl_kmeans_get_num_repetitions(kmeans);
//const vl_type data_type = vl_kmeans_get_data_type(kmeans);
//
{
const float *centers = (float *)vl_kmeans_get_centers(kmeans);
for (int i = 0; i < num_clusters; ++i)
{
std::cout << '(';
for (int j = 0; j < data_dim; ++j)
{
if (j) std::cout << ',';
std::cout << centers[i * data_dim + j];
}
std::cout << ')' << std::endl;
}
}
//
{
vl_uint32 assignments[num_data] = { 0, };
double distances[num_data] = { 0, };
vl_kmeans_quantize(kmeans, assignments, (void *)distances, (void const *)data, num_data);
for (int i = 0; i < num_data; ++i)
{
std::cout << '(';
for (int j = 0; j < data_dim; ++j)
{
if (j) std::cout << ',';
std::cout << data[i * data_dim + j]; // TODO [check] >> is it correct?
}
std::cout << ") => " << assignments[i] << std::endl;
}
}
std::cout << "end processing ..." << std::endl;
//
if (kmeans)
{
vl_kmeans_delete(kmeans);
kmeans = NULL;
}
}
bool VLFeat::CalculateCommon(int f, bool all, int l) {
string msg = "VLFeat::CalculateCommon("+ToStr(f)+","+ToStr(all)+","+
ToStr(l)+") : ";
// if (!do_fisher && !do_vlad) {
// cerr << msg
// << "either encoding=fisher or encoding=vlad should be specified"
// << endl;
// return false;
// }
if (!gmm && !kmeans) {
cerr << msg << "either gmm=xxx or kmeans=xxx option should be given"
<< endl;
return false;
}
cox::tictac::func tt(tics, "VLFeat::CalculateCommon");
// obs! only some parameters here, should be in ProcessOptionsAndRemove()
// too, also scales and geometry should be made specifiable...
bool normalizeSift = false, renormalize = true, flat_window = true;
size_t step = 3, binsize = 8;
EnsureImage();
int width = Width(true), height = Height(true);
if (FrameVerbose())
cout << msg+"wxh="
<< width << "x" << height << "=" << width*height << endl;
vector<float> rgbcoeff { 0.2989, 0.5870, 0.1140 };
imagedata idata = CurrentFrame();
idata.convert(imagedata::pixeldata_float);
idata.force_one_channel(rgbcoeff);
vector<float> dsift;
size_t descr_size_orig = 0, descr_size_final = 0;
vector<float> scales { 1.0000, 0.7071, 0.5000, 0.3536, 0.2500 };
// vector<float> scales { 1.0000 };
for (size_t i=0; i<scales.size(); i++) {
if (KeyPointVerbose())
cout << "Starting vl_dsift_process() in scale " << scales[i] << endl;
imagedata simg = idata;
if (scales[i]!=1) {
scalinginfo si(simg.width(), simg.height(),
(int)floor(scales[i]*simg.width()+0.5),
(int)floor(scales[i]*simg.height()+0.5));
simg.rescale(si, 1);
}
// VlDsiftFilter *sf = vl_dsift_new(simg.width(), simg.height());
VlDsiftFilter *sf = vl_dsift_new_basic(simg.width(), simg.height(),
step, binsize);
// opts.scales = logspace(log10(1), log10(.25), 5) ;
// void vl_dsift_set_bounds ( VlDsiftFilter * self,
// int minX,
// int minY,
// int maxX,
// int maxY
// );
// VlDsiftDescriptorGeometry geom = { 8, 4, 4, 0, 0 };
// vl_dsift_set_geometry(sf, &geom);
//vl_dsift_set_steps(sf, 3, 3);
//vl_dsift_set_window_size(sf, 8);
vl_dsift_set_flat_window(sf, flat_window); // aka fast in matlab
vector<float> imgvec = simg.get_float();
const float *img_fp = &imgvec[0];
// cout << "IMAGE = " << img_fp[0] << " " << img_fp[1] << " "
// << img_fp[2] << " ... " << img_fp[41] << endl;
vl_dsift_process(sf, img_fp);
// if opts.rootSift // false
// descrs{si} = sqrt(descrs{si}) ;
// end
// if opts.normalizeSift //true
// descrs{si} = snorm(descrs{si}) ;
// end
descr_size_orig = sf->descrSize;
size_t nf = sf->numFrames;
const VlDsiftKeypoint *k = sf->frames;
float *d = sf->descrs;
if (KeyPointVerbose())
cout << " found " << sf->numFrames << " 'frames' in "
<< simg.info() << endl
<< " descriptor dim " << descr_size_orig << endl;
if (PixelVerbose())
for (size_t i=0; i<nf; i++) {
cout << " i=" << i << " x=" << k[i].x << " y=" << k[i].y
<< " s=" << k[i].s << " norm=" << k[i].norm;
if (FullVerbose()) {
cout << " RAW";
for (size_t j=0; j<descr_size_orig; j++)
cout << " " << d[i*descr_size_orig+j];
}
cout << endl;
}
if (normalizeSift) {
for (size_t i=0; i<nf; i++) {
if (PixelVerbose())
cout << " i=" << i << " x=" << k[i].x << " y=" << k[i].y
<< " s=" << k[i].s << " norm=" << k[i].norm;
double mul = 0.0;
for (size_t j=0; j<descr_size_orig; j++)
mul += d[i*descr_size_orig+j]*d[i*descr_size_orig+j];
if (mul)
mul = 1.0/sqrt(mul);
if (FullVerbose())
cout << " NORM";
for (size_t j=0; j<descr_size_orig; j++) {
d[i*descr_size_orig+j] *= mul;
if (FullVerbose())
cout << " " << d[i*descr_size_orig+j];
}
if (PixelVerbose())
cout << endl;
}
}
if (!pca.vector_length()) {
dsift.insert(dsift.end(), d, d+nf*descr_size_orig);
descr_size_final = descr_size_orig;
} else {
for (size_t i=0; i<nf; i++) {
vector<float> vin(d+i*descr_size_orig, d+(i+1)*descr_size_orig);
vector<float> vout = pca.projection_coeff(vin);
dsift.insert(dsift.end(), vout.begin(), vout.end());
}
descr_size_final = pca.base_size();
}
vl_dsift_delete(sf);
}
size_t numdata = dsift.size()/descr_size_final;
const float *datain = &dsift[0];
vector<float> enc((do_fisher?2:1)*descriptor_dim()*nclusters());
float *dataout = &enc[0];
if (do_fisher) {
if (FrameVerbose())
cout << msg << "fisher encoding " << numdata
<< " descriptors of size " << descr_size_orig
<< " => " << descr_size_final
<< " with gmm dimensionality " << descriptor_dim()
<< endl;
if (descr_size_final!=descriptor_dim()) {
cerr << msg << "dimensionality mismatch descr_size_final="
<< descr_size_final << " descriptor_dim()=" << descriptor_dim()
<< endl;
return false;
}
vl_fisher_encode(dataout, VL_TYPE_FLOAT, means(), descriptor_dim(),
nclusters(), covariances(), priors(),
datain, numdata, VL_FISHER_FLAG_IMPROVED) ;
}
if (do_vlad) {
//obs! correct use of pca?
if (FrameVerbose())
cout << msg << "vlad encoding " << numdata
<< " descriptors of size " << descr_size_final << endl;
vector<vl_uint32> indexes(numdata);
vector<float> distances(numdata);
if (kdtree)
vl_kdforest_query_with_array(kdtree, &indexes[0], 1, numdata, &distances[0], datain);
else
vl_kmeans_quantize(kmeans, &indexes[0], &distances[0], datain, numdata);
vector<float> assignments(numdata*nclusters());
for (size_t i=0; i<numdata; i++)
assignments[i * nclusters() + indexes[i]] = 1;
int vlad_flags = VL_VLAD_FLAG_SQUARE_ROOT|VL_VLAD_FLAG_NORMALIZE_COMPONENTS;
vl_vlad_encode(dataout, VL_TYPE_FLOAT, means(), descriptor_dim(),
nclusters(), datain, numdata, &assignments[0],
vlad_flags);
}
if (renormalize) {
if (PixelVerbose())
cout << " RENORM:";
double mul = 0.0;
for (size_t j=0; j<enc.size(); j++)
mul += enc[j]*enc[j];
if (mul)
mul = 1.0/sqrt(mul);
for (size_t j=0; j<enc.size(); j++) {
if (PixelVerbose())
cout << " " << enc[j];
enc[j] *= mul;
if (PixelVerbose())
cout << "->" << enc[j];
}
if (PixelVerbose())
cout << endl;
}
((VectorData*)GetData(0))->setVector(enc);
return true;
}
