Comments (5)
It's true that there is some extra memory for the proposal models, but this should be small in comparison with the memory for the full model, since the proposal models are lower-resolution and have shorter features. The proposal models are just there to improve speed but they shouldn't affect quality, so you could run with an even lower-resolution proposal model, or without a proposal model, if memory is an issue.
from k-planes.
Thanks for your reply! Just try to make it more clear: here is the report model params:
here is the size of provided model:
The two sizes look quite different, just want to know if I misunderstand something.
from k-planes.
I understand that params may not mean the model size.
But it is still a little strange, e.g., params of TensoRF is 18 M and model size is 72 MB.
For K-Planes, params is 34M and model size is 384 MB.
from k-planes.
This is interesting; I have some suspicion as to what is happening.
- Part of the gap is because the "M" in params is "millions" not "megabytes", so for fp32 there's a factor of 4 difference.
- The saved model (at least for kplanes) includes the optimizer state, which for Adam requires a lot of memory (roughly 2x the size of the model, because it keeps two running averages of the gradient to adapt the step sizes). I would suspect that the memory of just the model itself should be about 1/3 of the size of the .pth file because of this.
from k-planes.
This is interesting; I have some suspicion as to what is happening.
- Part of the gap is because the "M" in params is "millions" not "megabytes", so for fp32 there's a factor of 4 difference.
- The saved model (at least for kplanes) includes the optimizer state, which for Adam requires a lot of memory (roughly 2x the size of the model, because it keeps two running averages of the gradient to adapt the step sizes). I would suspect that the memory of just the model itself should be about 1/3 of the size of the .pth file because of this.
Great, that makes senes! Thanks for the explanation.
from k-planes.
Related Issues (20)
- Please provide a set of parameters to reproduce the results on the lego dataset HOT 2
- Training on Custom Data HOT 4
- Visualization/Evaluation ERROR HOT 4
- Mismatch in total variation loss between description in paper and the implementation HOT 2
- OOM issue HOT 3
- Question about result of DyNeRF dataset : a difference between the results in the paper and my results HOT 6
- Bad performance on other dataset. HOT 4
- Questions about planes HOT 1
- Performance on TanksandTemple dataset HOT 2
- Replicating Fig 8 from the paper HOT 2
- IndexError at "video_datasets.py" HOT 1
- why is ndc_far=2.6 and not 1?
- About average_poses function?
- Query Regarding 'bds.npy' File in K-Planes Dataset HOT 1
- Temporal difference (IST) strategy HOT 4
- About Bilinear interpolation?
- Inconsistent Results Despite Setting Random Seed HOT 2
- used coordinate system in Phototourism
- Image Height and Width Flipped for D-NeRF scenes
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 k-planes.