MCPcopy Index your code
hub / github.com/CompVis/diff2flow / compute_xt

Method compute_xt

diff2flow/flow.py:552–571  ·  view source on GitHub ↗

Sample from the time-dependent density p_t xt ~ N(alpha_t * x1 + sigma_t * x0, sigma_min * I), according to Eq. (1) in [3] and for the linear schedule Eq. (14) in [2]. Args: x0 : shape (bs, *dim), represents the source minibatch (noise) x

(self, x0: Tensor, x1: Tensor, t: Tensor)

Source from the content-addressed store, hash-verified

550 """ Training """
551
552 def compute_xt(self, x0: Tensor, x1: Tensor, t: Tensor):
553 """
554 Sample from the time-dependent density p_t
555 xt ~ N(alpha_t * x1 + sigma_t * x0, sigma_min * I),
556 according to Eq. (1) in [3] and for the linear schedule Eq. (14) in [2].
557
558 Args:
559 x0 : shape (bs, *dim), represents the source minibatch (noise)
560 x1 : shape (bs, *dim), represents the target minibatch (data)
561 t : shape (bs,) represents the time in [0, 1]
562 Returns:
563 xt : shape (bs, *dim), sampled point along the time-dependent density p_t
564 """
565 t = pad_v_like_x(t, x0)
566 alpha_t = self.schedule.alpha_t(t)
567 sigma_t = self.schedule.sigma_t(t)
568 xt = alpha_t * x1 + sigma_t * x0
569 if self.sigma_min > 0:
570 xt += self.sigma_min * torch.randn_like(xt)
571 return xt
572
573 def compute_ut(self, x0: Tensor, x1: Tensor, t: Tensor):
574 """

Callers 3

training_lossesMethod · 0.95
validation_lossesMethod · 0.95
training_lossesMethod · 0.80

Calls 3

pad_v_like_xFunction · 0.85
alpha_tMethod · 0.45
sigma_tMethod · 0.45

Tested by

no test coverage detected