Comments (13)
From the log, it looks like you are using cuda v11.7, the requirements.txt will install packages that are not compatible with cuda v11.7 and python 3.7
First check your installed cuda version typing in a command prompt;
nvcc --version
If it says at the bottom;
Build cuda_11.7
Then run these commands, make sure you have activated your conda env first;
conda activate Gaussians4D
pip uninstall torch torchvision torchaudio
Then;
pip install torch==1.13.1+cu117 torchvision==0.14.1+cu117 torchaudio==0.13.1+cu117 --extra-index-url https://download.pytorch.org/whl/cu117
After that;
pip install -e submodules/depth-diff-gaussian-rasterization
pip install -e submodules/simple-knn
See how that goes, hopefully I found the right versions for you.
from 4dgaussians.
Should be up and running soon so stick with v11.7
The link I sent was missing the full version at the end - cu117, try with this;
pip install torch==1.13.1+cu117 torchvision==0.14.1+cu117 torchaudio==0.13.1+cu117 --extra-index-url https://download.pytorch.org/whl/cu117
The file is there so should be picked up
https://download.pytorch.org/whl/torch/
from 4dgaussians.
emm, the log said No CUDA runtime is found, using CUDA_HOME='C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7'
maybe the path of cuda is not confirmed?
from 4dgaussians.
pip install torch==1.13.1+cu117 torchvision==0.14.1+cu117 torchaudio==1.3.1+cu117 --extra-index-url https://download.pytorch.org/whl/cu117
this gives me this error:
ERROR: Could not find a version that satisfies the requirement torchaudio==1.3.1+cu117 (from versions: 0.6.0, 0.7.0, 0.7.1, 0.7.2, 0.8.0, 0.8.1, 0.9.0, 0.9.1, 0.10.0, 0.10.1, 0.10.2, 0.11.0, 0.12.0, 0.12.1, 0.13.0, 0.13.0+cu117, 0.13.1, 0.13.1+cu117)
ERROR: No matching distribution found for torchaudio==1.3.1+cu117
from 4dgaussians.
emm, the log said
No CUDA runtime is found, using CUDA_HOME='C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.7'
maybe the path of cuda is not confirmed?
I had this in my system PATH
from 4dgaussians.
The version number was incorrect, 1.3.1 should be 0.13.1, try this;
pip install torch==1.13.1+cu117 torchvision==0.14.1+cu117 torchaudio==0.13.1+cu117 --extra-index-url https://download.pytorch.org/whl/cu117
from 4dgaussians.
The version number was incorrect, 1.3.1 should be 0.13.1, try this;
pip install torch==1.13.1+cu117 torchvision==0.14.1+cu117 torchaudio==0.13.1+cu117 --extra-index-url https://download.pytorch.org/whl/cu11
Still getting error
(Gaussians4D) Y:\AI\4DGaussians>pip install torch==1.13.1+cu117 torchvision==0.14.1+cu117 torchaudio==0.13.1+cu117 --extra-index-url https://download.pytorch.org/whl/cu11
Looking in indexes: https://pypi.org/simple, https://download.pytorch.org/whl/cu11
ERROR: Could not find a version that satisfies the requirement torch==1.13.1+cu117 (from versions: 1.7.0, 1.7.1, 1.8.0, 1.8.1, 1.9.0, 1.9.1, 1.10.0, 1.10.1, 1.10.2, 1.11.0, 1.12.0, 1.12.1, 1.13.0, 1.13.1)
ERROR: No matching distribution found for torch==1.13.1+cu117
would it be easier if I install another CUDA version?
from 4dgaussians.
I have successfully built it with CUDA 11.8, Python 3.11.4 and PyTorch 2.0.1 (I had no success with Python 3.7, Torch 1.13.1 and CUDA 11.6).
from 4dgaussians.
I used Python 3.10 and
pip install torch==2.1.0+cu118 torchvision==0.16.0+cu118 torchaudio==2.1.0+cu118 --extra-index-url https://download.pytorch.org/whl/cu118
from 4dgaussians.
Should be up and running soon so stick with v11.7
The link I sent was missing the full version at the end - cu117, try with this;
pip install torch==1.13.1+cu117 torchvision==0.14.1+cu117 torchaudio==0.13.1+cu117 --extra-index-url https://download.pytorch.org/whl/cu117
The file is there so should be picked up https://download.pytorch.org/whl/torch/
aparently this one worked! Thanx a lot @henrypearce4D
from 4dgaussians.
Thanks for everyone!
from 4dgaussians.
CUDA Version:
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2019 NVIDIA Corporation
Built on Sun_Jul_28_19:07:16_PDT_2019
Cuda compilation tools, release 10.1, V10.1.243
I have built with,
pip install torch==1.8.1+cu101 torchvision==0.9.1+cu101 torchaudio==0.8.1 -f https://download.pytorch.org/whl/torch_stable.html
However, there are some problems, how can I solve it
from 4dgaussians.
From the log, it looks like you are using cuda v11.7, the requirements.txt will install packages that are not compatible with cuda v11.7 and python 3.7
First check your installed cuda version typing in a command prompt;
nvcc --version
If it says at the bottom;
Build cuda_11.7
Then run these commands, make sure you have activated your conda env first;
conda activate Gaussians4D
pip uninstall torch torchvision torchaudio
Then;
pip install torch==1.13.1+cu117 torchvision==0.14.1+cu117 torchaudio==0.13.1+cu117 --extra-index-url https://download.pytorch.org/whl/cu117
After that;
pip install -e submodules/depth-diff-gaussian-rasterization
pip install -e submodules/simple-knn
See how that goes, hopefully I found the right versions for you.
That solved it for me, thank you!
from 4dgaussians.
Related Issues (20)
- Tutorial, explanation and troubleshooting
- frame ranges on custom dataset HOT 1
- Error installing submodules HOT 5
- No module named 'tkinter' HOT 4
- Render From specific viewpoint HOT 1
- AssertionError: Could not recognize scene type! HOT 3
- GPU Usage 100% at dataloading while not proceeding HOT 2
- Problem with custom stereo dataset HOT 2
- train.py gives me "loss is nan" as soon as it starts training HOT 2
- SIBR viewer not working on custom data HOT 3
- Render from a new viewpoint HOT 1
- Error when Training (in gaussian_renderer/__init__.py, ValueError: not enough values to unpack) HOT 3
- simple question - Is it applicable for multiple cameras? HOT 2
- error multipleviewprogress HOT 1
- New scene generalization HOT 1
- Parameter Optimization HOT 3
- Question : Difference between Coarse and Fine Training HOT 1
- About DSSIM Loss and opacity reset HOT 2
- Test
- python setup.py develop did not run successfully. 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 4dgaussians.