MCG-NJU / EMA-VFI

[CVPR 2023] Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolatio
Apache License 2.0
399 stars 42 forks source link

Running out of ram on large 4k images #24

Open luuude opened 10 months ago

luuude commented 10 months ago

Hi and conratulations on this awesome work!

I have been experimenting with this abit and I run out of ram when using the large model on 4k images when running on 24GB gpu

Any ideas on how to process large images on 24GB?

I am going to test splitting it up i four pieces and reassembling but I fear there will be seams.

jhogsett commented 8 months ago

@luuude I have successfully processed 4K content on my RTX 3090 w/ 24GB, BUT:

I've concluded it's not worth interpolating 4K content with this hardware.

I've also thought about tiling, but that would likely interfere with the engine's ability to recognize objects and estimate motion, creating odd seams.

luuude commented 8 months ago

90 seconds is quite rough but for VFX rendering not that bad. Usually I work with quite short cuts under 100 frames. How do you enable the NVIDIA feature to overflow into system RAM?

jhogsett commented 8 months ago

In the "NVIDIA Control Panel" under "Manage 3D Settings" I have this option:

"CUDA - Sysmem Fallback Policy"