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

Method _prior_bpd

guided_diffusion/gaussian_diffusion.py:827–843  ·  view source on GitHub ↗

Get the prior KL term for the variational lower-bound, measured in bits-per-dim. This term can't be optimized, as it only depends on the encoder. :param x_start: the [N x C x ...] tensor of inputs. :return: a batch of [N] KL values (in bits), one per batch

(self, x_start)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers 1

calc_bpd_loopMethod · 0.95

Calls 4

q_mean_varianceMethod · 0.95
normal_klFunction · 0.85
mean_flatFunction · 0.85
logMethod · 0.45

Tested by

no test coverage detected