Comments (5)
Hi, did you use the conda environment specified in environment.yml
? I suspect this is a TF version issue.
Regarding the trained model, yes, I will release them soon.
from nerfactor.
Thanks for your reply! i have addressed the problem after changing TF version.
and when I run the step 'geometry_from_nerf' I need to spend very long time to run, maybe over 2 days. Is this normal?
thanks again!
from nerfactor.
Hi, I have similar question as what @XiaoKangW asked.
So I think geometry_from_nerf
takes really long as mentioned in your paper:
"Prior to the final joint optimization, computing the initial surface normals and light visibility from the trained NeRF takes 30 minutes per view on a single GPU for a 16 × 32 light probe (i.e., 512 light source locations)."
I currently have three 2080ti available with me. It has way much less GPU RAM size (11G) compared to your Titan RTX (24G).
I was about to parallelize the process and use multi-GPU to speed up, but it says in 3rd step of prep that I only have to use a single GPU:
"For portability, this step runs sequentially, processing one view after another. If your infrastructure supports distributing jobs easily over multiple GPUs, you should consider having one GPU process one view to parallelize all views."
And in your paper, you mentioned that this geometry calculation step can be:
"trivially parallelized because each view is processed independently."
I am quite confused how to parallelize it. Do you have any options in your bash script to do so or do I have to modify your script? Thank you in advance for your help.
FYI: It took 6 days for me to finish train/validation/test steps to calculate the surface normals and light visibility, with a single 2080ti.
from nerfactor.
Hi, xiuming,
I came across the similar issue , I try to generate geometry in parallel but current settings only allow me to generate geometry sequentially. Could you please give me some suggestion how to parallelize these?
Thank you very much!
from nerfactor.
Sorry for the delayed response, @cjw531 and @xilongzhou.
In these lines:
https://github.com/google/nerfactor/blob/main/nerfactor/geometry_from_nerf.py#L85-L87
we are calling process_view()
in a for-loop, sequentially.
To parallelize this step, we had one GPU running process_view()
per view. Because how to parallelize all views depends highly on what your infrastructure is, we released this sequential version for portability.
LMK if you have further questions.
from nerfactor.
Related Issues (20)
- The pre-trained models and data provided are not sufficient to perform tests on the blender dataset HOT 3
- How to calculate geometry buffers from MVS geometry ? HOT 1
- Rendering scripts HOT 1
- questions about hdrs. HOT 1
- Question about incompatible shapes(0,3) and (100,3) at II. Joint Optimization in Training, Validation, and Testing HOT 19
- gradient error in Joint Optimization HOT 6
- brdf_scale HOT 5
- MLPs wrong skip connection
- Crash at shape pre-training HOT 7
- OOM at II. Joint Optimization in Training, Validation, and Testing HOT 2
- Wrong NeRF and surface
- How long will it take to run the third part in the ./nerfactor HOT 1
- Rendering results are all white after training the vanilla NeRF in step1 HOT 1
- Shape error at II. Joint Optimization HOT 1
- Can we extract mesh from the system by marching cubes? HOT 1
- About create my own dataset
- Relighting Results Background Color HOT 1
- When I train vanilla nerf, there are countless threads.
- It is slow to render my own synthetic data, can we use gpu to render? HOT 1
- Shape pre-trained stage error 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 nerfactor.