Jeremy Rand
There are a bunch of configurable options in ncnn that affect memory usage. Winograd convolution is the main one -- it makes things much faster but also uses more memory....
Can you clarify how this PR compares to #2070? At first glance it looks like it may have some similar logic (but possibly used in different places?).
I see. Maybe there's some potential for reusing some of this for #2070's intended use case (CPU inference)? I think for my use cases in #2070, this UX would *almost*...
(Using a percentage of RAM rather than an explicit number as #2070 does is probably better UX.)
Oh, I see. That wasn't obvious to me from the screenshot. Yeah, so this UX seems better than #2070 for my use cases. I'd probably be OK with putting #2070...
> > Oh, I see. That wasn't obvious to me from the screenshot. > > Maybe I need to reword this. Instead of **Use total system memory** something like **Apply...
> I was thinking about this, but free RAM differs so much, that showing the user a number would let them assume that it might always be the displayed value....
How would you feel about making the percentage precise to 0.1% rather than 1%? On systems with a lot of RAM (my main system has around 300 GiB), being more...
Very nice, I'll rebase #2070 after this is merged.
What would be needed at this point to move this forward? You mentioned hardware access -- what would be the obstacles to doing this with remote access?