How to calculate KL-divergence in multivariate Gaussian distribution is the following code correct?
mu, logvar = self.encode(x.view(-1, 2))
z = self.reparameterize(mu, logvar)
#q0 = torch.distributions.normal.Normal(mu, (0.5 * logvar).exp())
q0 = MultivariateNormal(mu, (0.5 * logvar).exp())
# prior = torch.distributions.normal.Normal(0., 1.)
prior = MultivariateNormal(mu,logvar)
log_prior_z = prior.log_prob(z).sum(-1)
log_q_z = q0.log_prob(z).sum(-1)
KL = log_q_z - log_prior_z