白致远
白致远
I tried but sttill out of memory. gaussian splatting model used about 4000x 4k photo.my device has 660g ram and 3x tesla l20 48Gb vram. date put into cpu memory
> Each image was 4MB and you had 4000 of them? How many splats were in your scene when it crashed? 
4`396`589,this is the pointcloud file before compression
I tried by a 1.1TB RAM device.still out of memory
It`s all the time,and anyway to fix it? ________________________________ 发件人: Andrew Ryan Carpenter ***@***.***> 发送时间: 2024年11月12日 9:15 收件人: KeKsBoTer/c3dgs ***@***.***> 抄送: 白致远 ***@***.***>; Comment ***@***.***> 主题: Re: [KeKsBoTer/c3dgs] Optimize Lazy...
> I need to dig up the code again and take a look. I know we had this issue fixed. Is this a time sensitive issue for you? so anyway...
> Use something like this: > > ``` > def lazy_call(f, *args, **kwargs): > return lambda: f(*args, **kwargs) > > def cameraList_from_camInfos(cam_infos, resolution_scale, args, lazy_load): > camera_list = [] >...
qualcomm trustfirmware maybe have bug
btw you can try the multirom-dev.it used keep hardboot
did you fixed it? and how many memory it cost when you put data to cpu-ram?