def most_likely_states(self, data, input=None, mask=None, tag=None): log_pi0 = self.init_state_distn.log_initial_state_distn( data, input, mask, tag) log_Ps = self.transitions.log_transition_matrices( data, input, mask, tag) log_likes = self.observations.log_likelihoods(data, input, mask, tag) return viterbi(log_pi0, log_Ps, log_likes)
def most_likely_states(self, data, input=None, mask=None, tag=None): m = self.state_map log_pi0 = self.init_state_distn.log_initial_state_distn(data, input, mask, tag) log_Ps = self.transitions.log_transition_matrices(data, input, mask, tag) log_likes = self.observations.log_likelihoods(data, input, mask, tag) z_star = viterbi(replicate(log_pi0, m), log_Ps, replicate(log_likes, m)) return self.state_map[z_star]
def most_likely_states(self, variational_mean, data, input=None, mask=None, tag=None): log_pi0 = self.init_state_distn.log_initial_state_distn( variational_mean, input, mask, tag) log_Ps = self.transitions.log_transition_matrices( variational_mean, input, mask, tag) log_likes = self.dynamics.log_likelihoods( variational_mean, input, np.ones_like(variational_mean, dtype=bool), tag) log_likes += self.emissions.log_likelihoods(data, input, mask, tag, variational_mean) return viterbi(log_pi0, log_Ps, log_likes)