"CUDA out of memory" on RTX3090

[aKijia]

Hello,

got this error while tried to interpolate 1 hour 24FPS 576p video into 48FPS closer to its end (83101 frame of 95203)

RuntimeError: CUDA out of memory. Tried to allocate 1.14 GiB (GPU 0; 24.00 GiB total capacity; 439.51 MiB already allocated; 21.30 GiB free; 632.00 MiB reserved in total by PyTorch)

After I restarted system and deleted last interpolated frames i got this

RuntimeError: CUDA out of memory. Tried to allocate 8.66 GiB (GPU 0; 24.00 GiB total capacity; 144.61 MiB already allocated; 13.53 GiB free; 8.39 GiB reserved in total by PyTorch)

Have no idea why all this free memory can't be used here.

r7 5800x, 32GB@4000MHz, RTX3090

[bropines]

I also got this error. Probably python can't take more memory from the graphics card. Waiting for the fix

[Khipucamayoc]

Hi! If you could share how you managed to make it run with the RTX 3090 I would be most grateful!
I am getting so many errors I don't know where to start fixing them...

I am using:

Ubuntu 20.04
PyTorch 1.9 & Anaconda
env python=3.8
CUDA 11.1 RTX 3090

I changed the PyTorch as recommended to my env name in ./build.sh but still does not work...

I have even changed the compiler arguments (https://github.com/baowenbo/DAIN/files/7402642/compiler_args.txt) as recommended but nothing...

Thanks!

[bropines]

Привет! Если бы вы могли поделиться, как вам удалось заставить его работать с RTX 3090, я был бы очень благодарен! У меня так много ошибок, что я не знаю, с чего начать их исправлять ...

Я использую:

Ubuntu 20.04 PyTorch 1.9 и Anaconda env python = 3.8 CUDA 11.1 RTX 3090

Я изменил PyTorch, как рекомендовано для моего имени env в ./build.sh, но все еще не работает ...

Я даже изменил аргументы компилятора ( https://github.com/baowenbo/DAIN/files/7402642/compiler_args.txt ), как рекомендовано, но ничего ...

Спасибо!

Maybe use FlowFrames.This is a program with a built-in dain.