MCPcopy Create free account
hub / github.com/Meshcapade/difflocks / get_sigmas_exponential

Function get_sigmas_exponential

k_diffusion/sampling.py:26–29  ·  view source on GitHub ↗

Constructs an exponential noise schedule.

(n, sigma_min, sigma_max, device='cpu')

Source from the content-addressed store, hash-verified

24
25
26def get_sigmas_exponential(n, sigma_min, sigma_max, device='cpu'):
27 """Constructs an exponential noise schedule."""
28 sigmas = torch.linspace(math.log(sigma_max), math.log(sigma_min), n, device=device).exp()
29 return append_zero(sigmas)
30
31
32def get_sigmas_polyexponential(n, sigma_min, sigma_max, rho=1., device='cpu'):

Callers

nothing calls this directly

Calls 1

append_zeroFunction · 0.85

Tested by

no test coverage detected