NextCloud/dlib
1
0
Fork 0
mirror of https://github.com/davisking/dlib.git synced 2024-11-01 10:14:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

minor cleanup

Browse Source
This commit is contained in:
Davis King 2011-06-03 22:35:05 -04:00
parent 94067a7666
commit 3bc36fe1a2
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
examples/using_custom_kernels_ex.cpp
View File

@ -100,7 +100,7 @@ void deserialize ( ukf_kernel<T>& item, std::istream& in )
// ---------------------------------------------------------------------------------------- // ----------------------------------------------------------------------------------------
/* /*
This next thing, the kernel_derivative specialization is OPTIONAL. You only need This next thing, the kernel_derivative specialization is optional. You only need
to define it if you want to use the dlib::reduced2() or dlib::approximate_distance_function() to define it if you want to use the dlib::reduced2() or dlib::approximate_distance_function()
routines. If so, then you need to supply code for computing the derivative of your kernel as routines. If so, then you need to supply code for computing the derivative of your kernel as
shown below. Note also that you can only do this if your kernel operates on dlib::matrix shown below. Note also that you can only do this if your kernel operates on dlib::matrix
@ -166,7 +166,7 @@ int main()
// A valid kernel must always give rise to kernel matrices which are symmetric // A valid kernel must always give rise to kernel matrices which are symmetric
// and positive semidefinite (i.e. have nonnegative eigenvalues). This next // and positive semidefinite (i.e. have nonnegative eigenvalues). This next
// bit of code makes a kernel matrix and checks if this is true. // bit of code makes a kernel matrix and checks if it has these properties.
const matrix<double> K = kernel_matrix(kernel_type(0.1), randomly_subsample(samples, 500)); const matrix<double> K = kernel_matrix(kernel_type(0.1), randomly_subsample(samples, 500));
cout << "\nIs it symmetric? (this value should be 0): "<< min(abs(K - trans(K))) << endl; cout << "\nIs it symmetric? (this value should be 0): "<< min(abs(K - trans(K))) << endl;
cout << "Smallest eigenvalue (should be >= 0): " << min(real_eigenvalues(K)) << endl; cout << "Smallest eigenvalue (should be >= 0): " << min(real_eigenvalues(K)) << endl;