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
haohang96 opened this issue 2 years ago · comments
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.