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

Method calc_bpd_loop

guided_diffusion/gaussian_diffusion.py:845–900  ·  view source on GitHub ↗

Compute the entire variational lower-bound, measured in bits-per-dim, as well as other related quantities. :param model: the model to evaluate loss on. :param x_start: the [N x C x ...] tensor of inputs. :param clip_denoised: if True, clip denoised samples.

(self, model, x_start, clip_denoised=True, model_kwargs=None)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers

nothing calls this directly

Calls 5

q_sampleMethod · 0.95
_vb_terms_bpdMethod · 0.95
_prior_bpdMethod · 0.95
mean_flatFunction · 0.85

Tested by

no test coverage detected