Giters

yang-song / score_sde

Official code for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)

Home Page:https://arxiv.org/abs/2011.13456

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Questions about Alg. 5 in the paper

haohang96 opened this issue · comments

commented

I wondered why the step size $\epsilon$ of VP SDE in corrector need to multiply a more $\alpha_i$ compared with $\epsilon$ in VE SDE setting.