FluxML/Zygote.jl

gradient of keyword argument?

Open

#446 建立於 2020年1月6日

在 GitHub 查看
 (10 留言) (0 反應) (0 負責人)Julia (1,568 star) (220 fork)batch import
discussionhelp wantedperformance

描述

Is there any ways to compute the backward gradient of a keyword argument? For example, the var function can pass a pre-computed mean value as a keyword argument, but right now it seems like we can't get the gradient of it. This will have an effect on something like Flux.normalise.

貢獻者指南