ott.neural.methods.flows.dynamics.BaseFlow

class ott.neural.methods.flows.dynamics.BaseFlow(sigma)

Base class for all flows.

Parameters:

sigma (float) – Noise used for computing time-dependent noise schedule.

Methods

compute_mu_t(t, src, tgt)	Compute the mean of the probability path.
compute_sigma_t(t)	Compute the standard deviation of the probability path at time \(t\).
compute_ut(t, src, tgt)	Evaluate the conditional vector field.
compute_xt(rng, t, src, tgt)	Sample from the probability path.