p_scales.push_back(std::pow(p_scale_step, i));
#ifdef CUFFT
- if (Fft::freq_size(feature_size).area() > 1024) {
- std::cerr << "Window after forward FFT is too big for CUDA kernels. Plese use -f to set "
- "the window dimensions so its size is less or equal to "
- << 1024 * p_cell_size * p_cell_size * 2 + 1
- << " pixels. Currently the size of the window is: " << fit_size
- << " which is " << fit_size.area() << " pixels. " << std::endl;
- std::exit(EXIT_FAILURE);
- }
-
if (m_use_linearkernel) {
std::cerr << "cuFFT supports only Gaussian kernel." << std::endl;
std::exit(EXIT_FAILURE);
d.threadctxs.emplace_back(feature_size, p_num_of_feats, p_num_scales);
#endif
- gaussian_correlation.reset(new GaussianCorrelation(1, feature_size));
+ gaussian_correlation.reset(new GaussianCorrelation(1, p_num_of_feats, feature_size));
p_current_center = p_init_pose.center();
p_current_scale = 1.;
{
TRACE("");
xf.sqr_norm(xf_sqr_norm);
+ DEBUG_PRINTM(xf_sqr_norm[0]);
if (auto_correlation) {
yf_sqr_norm = xf_sqr_norm;
} else {
yf.sqr_norm(yf_sqr_norm);
}
+ DEBUG_PRINTM(yf_sqr_norm[0]);
xyf = auto_correlation ? xf.sqr_mag() : xf * yf.conj(); // xf.muln(yf.conj());
DEBUG_PRINTM(xyf);
DEBUG_PRINTM(xyf_sum);
kcf.fft.inverse(xyf_sum, ifft_res);
DEBUG_PRINTM(ifft_res);
-#ifdef CUFFT
+#if 0 && defined(CUFFT)
// FIXME
cuda_gaussian_correlation(ifft_res.deviceMem(), k.deviceMem(), xf_sqr_norm.deviceMem(),
auto_correlation ? xf_sqr_norm.deviceMem() : yf_sqr_norm.deviceMem(), sigma,