mlpack: create Gaussian Mixture Model

mlpack::gmm::GMM creates a Gaussian Mixture Model with different constructors.

Create an empty Gaussian Mixture Model, with zero gaussians.

[sourcecode language="cpp"] template<typename FittingType = EMFit<>> mlpack::gmm::GMM< FittingType >::GMM() [/sourcecode]

Create a GMM with the given number of Gaussians, each of which have the specified dimensionality.

[sourcecode language="cpp"] template<typename FittingType = EMFit<>> mlpack::gmm::GMM< FittingType >::GMM( const size_t gaussians, // Number of Gaussians in this GMM. const size_t dimensionality // Dimensionality of each Gaussian. ) // Example usage // create a GMM with 3 6D Gaussians size_t gaussians = 3; size_t dimensionality = 6; mlpack::gmm::GMM<> gmm(gaussians,dimensionality); [/sourcecode]

Create a GMM with the given number of Gaussians, each of which have the specified dimensionality. Also, pass in an initialized FittingType class; this is useful in cases where the FittingType class needs to store some state.

[sourcecode language="cpp"] template<typename FittingType = EMFit<>> mlpack::gmm::GMM< FittingType >::GMM( const size_t gaussians, // Number of Gaussians in this GMM. const size_t dimensionality, // Dimensionality of each Gaussian. FittingType & fitter // Initialized fitting mechanism. ) [/sourcecode]

Create a GMM with the given means, covariances, and weights.

[sourcecode language="cpp"] template<typename FittingType = EMFit<>> mlpack::gmm::GMM< FittingType >::GMM( const std::vector< arma::vec > & means, // Means of the model. const std::vector< arma::mat > & covariances, // Covariances of the model. const arma::vec & weights // Weights of the model. ) [/sourcecode]

Create a GMM with the given means, covariances, and weights, and use the given initialized FittingType class. This is useful in cases where the FittingType class needs to store some state.

I am Charmie

メモとログ

mlpack: create Gaussian Mixture Model