Comments (9)
@Devlee247 Yes, I changed the concatenation operation of ID and depth to store them separately, and that bug is fixed. However, I still encounter errors in the FORWARD::render
function, and I suspect there are other unresolved issues in the FORWARD::render
function.
from gaussian-splatting.
Does it happen on the first iteration or later on? Can you check whether you have nans on any tensors fed to the rasterisation function?
from gaussian-splatting.
@PanagiotisP Yes, the issue tends to occur after iterating hundreds of times, but sometimes it may take thousands of iterations to appear. I have checked the input parameters and have not found any NaN values. However, I noticed that the error occurs because currtile
or prevtile
exceeds the length of ranges
, resulting in a memory out-of-bounds issue. At this point, currtile
or prevtile
are very large strange numbers, such as prevtile=3210786815
and currtile=1072937470
. Do you have any insights on this?
from gaussian-splatting.
No, I'm sorry. I'm not very familiar with the tiling procedure, so NaN was my best bet. In your place, I think, I would also check if extremely big scale values appear for some reason (e.g. due to a regularisation term gone bad). But other than that, your guess is as good as mine
from gaussian-splatting.
@baoachun Did you solve this problem? I also got a very large strange numbers (currtile, prevtile).
from gaussian-splatting.
@baoachun Thank you for sharing, I also fixed via adding torch.cuda.empty_cache() in the forward function. (GaussianSplatting pytorch Class)
from gaussian-splatting.
@Devlee247 Thank you for sharing, unfortunately, this method does not solve my problem.
from gaussian-splatting.
@PanagiotisP How to solve this problem which the gaussian primitives attributions turn to be Nan
when I train for thousands iterations? And I check the Nan value and turn all nan to 0, but in the rest iterations, all the loss come to be nan.
from gaussian-splatting.
I am not sure I can help with that, as nan
propagates instantly to everything. Usually, you want to ensure that you don't make any obvious illegal operations, like dividing with zeros, taking the log of a non-positive number etc.
from gaussian-splatting.
Related Issues (20)
- Using point cloud to seed gaussian splatting HOT 6
- How to input depth data HOT 1
- Where can I download the driving data sets you displayed?
- SIBR viewer cmake error on ubuntu 20.04
- [QUESTION] Limiting output size HOT 1
- How can i display multiple '.ply' files in SIBR gaussian viewer app together? HOT 1
- Problem of Real-Time Viewer HOT 4
- Training demonstration error: all gaussians have same sizes and shapes HOT 2
- refinement iteration - discrepancy from paper and potential bug
- Could I get transform matrix form Mip360 real world dataset?
- Will 16GB VRAM be ok? HOT 1
- Installation using isolated cuda toolkit binaries within the conda environment
- Unable to create Conda environment "Conda exception: PIP Failed" HOT 1
- Tipc & tricks for good model HOT 3
- Question on the cameras and the projection matrices HOT 8
- How do you debug CUDA code? HOT 1
- Minimum GPU/Memory Requirements
- External rendering : is the opacity taken into account during rasterization HOT 1
- Install submodules diff-gaussian-rasterization and simple-knn HOT 1
- strange training result HOT 7
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 gaussian-splatting.