MCPcopy Create free account
hub / github.com/Zhiyuan-R/Tiger-Diffusion / all_kl

Method all_kl

train_generation.py:413–421  ·  view source on GitHub ↗
(self, x0, clip_denoised=True)

Source from the content-addressed store, hash-verified

411 return self.diffusion._prior_bpd(x0)
412
413 def all_kl(self, x0, clip_denoised=True):
414 total_bpd_b, vals_bt, prior_bpd_b, mse_bt = self.diffusion.calc_bpd_loop(self._denoise, x0, clip_denoised)
415
416 return {
417 'total_bpd_b': total_bpd_b,
418 'terms_bpd': vals_bt,
419 'prior_bpd_b': prior_bpd_b,
420 'mse_bt':mse_bt
421 }
422
423
424 def _denoise(self, data, t):

Callers 1

trainFunction · 0.95

Calls 1

calc_bpd_loopMethod · 0.80

Tested by

no test coverage detected