Comments (3)
@luuude I have successfully processed 4K content on my RTX 3090 w/ 24GB, BUT:
- each frame takes about 90+ seconds to process, in some cases, twice that
- it only works if I enable the NVIDIA feature to overflow into system RAM
- My system has 64 GB system RAM and it allows the GPU to use 32 GB
- While interpolating, the total memory load on the GPU is 56GB!
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.
from ema-vfi.
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?
from ema-vfi.
In the "NVIDIA Control Panel" under "Manage 3D Settings" I have this option:
"CUDA - Sysmem Fallback Policy"
from ema-vfi.
Related Issues (20)
- encounter RuntimeError: unmatched '}' in format string when training for fixed-timestep interpolation HOT 1
- Can you provide arbitrary frame interpolation training code HOT 5
- how to run the MotionFormer locally?
- Be faster and better HOT 1
- The input mask of unet is that before sigmoid HOT 3
- MAde one click installer and new bat file to run it
- 关于附件的运行时间问题
- This error occurs when I train to the last batch_size of epoch2. Is there a problem with the data set? Should this path (/sequences//im3.png) contain images HOT 4
- What is the difference between ours_t and ours?
- About arbitrary time training
- Multi-frame context
- Output optical flow
- Help for a newbie
- Does a bad job on patterns, also insanely slow on high end hardware [RTX 2080 Super]
- How can I generate ours_t?
- Question about the number of training GPUs HOT 1
- About motion features HOT 1
- can do input key frames to get a fluent video? HOT 1
- How do I use the pre-trained model to continue training on my dataset? HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ema-vfi.