discussionhelp wantedperformance
Repository-Metriken
- Stars
- (1.568 Sterne)
- PR-Merge-Metriken
- (Durchschn. Merge 2T 16h) (39 gemergte PRs in 30 T)
Beschreibung
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.