Comments (6)
could you plz provide more details concerning rebuilding and reinstalling?I'm also making a try to a higher language feature dimension.
@Zhirui86
Hi, finally I figured out where the issue is:
if you met error like: RuntimeError: Function _RasterizeGaussiansBackward returned an invalid gradient at index 4 - got [2228907, 4] but expected shape compatible with [2228907, 3]
We need to edit following files:
-
LangSplat/submodules/langsplat-rasterization/cuda_rasterizer/config.h
change NUM_CHANNELS_language_feature to the desired dim. Delete the local package and rebuild it.- remember to remove LangSplat/submodules/langsplat-rasterization/build folder if you have one, otherwise, it will use the cache. -
LangSplat/scene/gaussian_model.py
https://github.com/minghanqin/LangSplat/blob/main/scene/gaussian_model.py#L206C1-L206C87
change the line:
language_feature = torch.zeros((self._xyz.shape[0], 3), device="cuda")
We need to initialize the language_feature as the desired dim here, as for me it should be:
language_feature = torch.zeros((self._xyz.shape[0], 4), device="cuda")
Cheers!
from langsplat.
Hello, did you solve the error in brackets by just creating a new environment?(RuntimeError: CUDA error: an illegal memory access was encountered
Compile with TORCH_USE_CUDA_DSA
to enable device-side assertions.)
from langsplat.
The issue was solved by creating a new environment on WSL2 cuda118. I am going to explore more to reproduce this issue.
Currently I met a new issue when changing language features dimensions to 4:
RuntimeError: Function RasterizeGaussiansBackward returned an invalid qradient at index 4 - got[2228907,4] but expected shape compatible with [2228907,3]
Any help would be appreciated!
from langsplat.
could you plz provide more details concerning rebuilding and reinstalling?I'm also making a try to a higher language feature dimension.
from langsplat.
Have you ever tried a 512-dimension feature?I can build successfully in a lower level while it turns out as follows when setting dimension into 512:
from langsplat.
Have you ever tried a 512-dimension feature?I can build successfully in a lower level while it turns out as follows when setting dimension into 512:
Hi! I have the similar issue. Have you resolved this problem?
from langsplat.
Related Issues (20)
- The configuration of eval code for differenct scenes HOT 1
- Can you provide the download link of lerf_ovs HOT 1
- Interface to query gaussian by text in 3d_ovs dataset HOT 2
- 文本查询的演示程序
- Quite poor rendering and eval result! Why! HOT 3
- Failed to build diff_gaussian_rasterization ERROR: Could not build wheels for diff_gaussian_rasterization, which is required to install pyproject.toml-based projects HOT 3
- Concerns about Dataset Usage and Discrepancies in Experimental Results HOT 5
- Cannot Run the training code. HOT 2
- could you update a new version of rasterizer that can render depth
- ValueError: 没有设置language feature HOT 1
- got an unexpected keyword argument 'include_feature' HOT 2
- On the issue of semantic mask segmentation in data processing.
- Problems encountered when processing my own scene HOT 1
- About "lerf_ovs/label the gt_foder"
- How to visualize 3D segmentation results like LERF?
- How to segmentated object only save and rendering?
- Inconsistency between reported metric and self-trained results
- Simultaneous training without checkpoint
- UnboundLocalError: local variable 'h' referenced before assignment HOT 2
- RuntimeError: CUDA out of memory.
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 langsplat.