isofit.inversion.inverse_mcmc

Classes

MCMCInversion

Module Contents

class MCMCInversion(full_config: Config, forward: ForwardModel)[source]

Bases: isofit.inversion.inverse.Inversion

iterations[source]

burnin[source]

regularizer[source]

proposal_scaling[source]

verbose[source]

restart_every[source]

stable_mvnpdf(mean, cov, x)[source]: Stable inverse via Singular Value Decomposition, using only the significant eigenvectors.

log_density(x, rdn_meas, geom, bounds)[source]: Log probability density combines prior and likelihood terms.

invert(rdn_meas, geom)[source]: Inverts a meaurement. Returns an array of state vector samples. Similar to Inversion.invert() but returns a list of samples.