MCPcopy Create free account
hub / github.com/MoonInTheRiver/DiffSinger / predict_start_from_noise

Method predict_start_from_noise

usr/diff/diffusion.py:235–239  ·  view source on GitHub ↗
(self, x_t, t, noise)

Source from the content-addressed store, hash-verified

233 return mean, variance, log_variance
234
235 def predict_start_from_noise(self, x_t, t, noise):
236 return (
237 extract(self.sqrt_recip_alphas_cumprod, t, x_t.shape) * x_t -
238 extract(self.sqrt_recipm1_alphas_cumprod, t, x_t.shape) * noise
239 )
240
241 def q_posterior(self, x_start, x_t, t):
242 posterior_mean = (

Callers 1

p_mean_varianceMethod · 0.95

Calls 1

extractFunction · 0.70

Tested by

no test coverage detected