MCPcopy Index your code
hub / github.com/DeepGraphLearning/DiffPack / t_to_sigma

Method t_to_sigma

diffpack/schedule.py:171–180  ·  view source on GitHub ↗

Transfer timesteps to standard deviation. Args: t (Tensor): timesteps ranging from 0 to 1 Returns: Tensor: standard deviation ranging from sigma_min to sigma_max

(self, t)

Source from the content-addressed store, hash-verified

169 self.mode = mode
170
171 def t_to_sigma(self, t):
172 """Transfer timesteps to standard deviation.
173
174 Args:
175 t (Tensor): timesteps ranging from 0 to 1
176
177 Returns:
178 Tensor: standard deviation ranging from sigma_min to sigma_max
179 """
180 return torch.exp(self.sigma_min_log + (self.sigma_max_log - self.sigma_min_log) * t)
181
182 @torch.no_grad()
183 def add_noise(self, x, t, x_mask=None):

Callers 4

add_noiseMethod · 0.95
stepMethod · 0.95
add_noiseMethod · 0.80
generateMethod · 0.80

Calls

no outgoing calls

Tested by

no test coverage detected