MCPcopy Create free account
hub / github.com/MultiPath/CopyNet / gaussian_kl_divergence

Function gaussian_kl_divergence

emolga/basic/objectives.py:59–86  ·  view source on GitHub ↗

Computes the KL-divergence of Gaussian variables from the standard one. Given two variable ``mean`` representing :math:`\\mu` and ``ln_var`` representing :math:`\\log(\\sigma^2)`, this function returns a variable representing the KL-divergence between the given multi-dimensional Gaussia

(mean, ln_var)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers

nothing calls this directly

Calls

no outgoing calls

Tested by

no test coverage detected