MCPcopy Create free account
hub / github.com/NVlabs/DiffPure / discretized_gaussian_log_likelihood

Function discretized_gaussian_log_likelihood

guided_diffusion/losses.py:58–85  ·  view source on GitHub ↗

Compute the log-likelihood of a Gaussian distribution discretizing to a given image. :param x: the target images. It is assumed that this was uint8 values, rescaled to the range [-1, 1]. :param means: the Gaussian mean Tensor. :param log_scales: the Gaussian log s

(x, *, means, log_scales)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers 1

_vb_terms_bpdMethod · 0.85

Calls 2

logMethod · 0.45

Tested by

no test coverage detected