Comments (11)
I had the same issue I and resolved it:
it seems there were multiple possible conflicts. I had to make sure the CUDA version is the same as suggested on
https://pytorch.org/get-started/locally/
furthermore make sure to uninstall any existing torch versions
pip uninstall torch
and re-do the local installation steps from the url before in my case I was on windows running cuda 11.8 (archive)
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
edit: a little helper.
you have to see CUDA in the output or it will keep in stuck state.
test.py
import torch
# Check if PyTorch is using the GPU
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(f"PyTorch is using: {device}")
# Print PyTorch version
print(f"PyTorch version: {torch.__version__}")
# Test a simple PyTorch tensor operation on the GPU
x = torch.tensor([2.0, 3.0], device=device)
y = torch.tensor([4.0, 5.0], device=device)
result = x * y
print(f"Result of tensor operation: {result}")
from shap-e.
resolved.
thanks @moo-the-cow
before
test.py
PyTorch is using: cpu
PyTorch version: 2.0.0+cpu
Result of tensor operation: tensor([ 8., 15.])
What I did.
pip uninstall torch
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu117
after
test.py
PyTorch is using: cuda
PyTorch version: 2.0.0+cu117
Result of tensor operation: tensor([ 8., 15.], device='cuda:0')
from shap-e.
I have the same problem.
from shap-e.
I was able to bypass the denoising by setting use_karras=False,
but now I have this:
from shap-e.
from shap-e.
i was able to fix this by changing the runtime type to use a gpu on google colab, for what its worth
from shap-e.
i was able to fix this by changing the runtime type to use a gpu on google colab, for what its worth
This work fine. Yes.
from shap-e.
I had the same issue I and resolved it: it seems there were multiple possible conflicts. I had to make sure the CUDA version is the same as suggested on https://pytorch.org/get-started/locally/ furthermore make sure to uninstall any existing torch versions
pip uninstall torch
and re-do the local installation steps from the url before in my case I was on windows running cuda 11.8 (archive)
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
edit: a little helper. you have to see CUDA in the output or it will keep in stuck state. test.py
import torch # Check if PyTorch is using the GPU device = torch.device("cuda" if torch.cuda.is_available() else "cpu") print(f"PyTorch is using: {device}") # Print PyTorch version print(f"PyTorch version: {torch.__version__}") # Test a simple PyTorch tensor operation on the GPU x = torch.tensor([2.0, 3.0], device=device) y = torch.tensor([4.0, 5.0], device=device) result = x * y print(f"Result of tensor operation: {result}")
No CUDA for Mac. :(
from shap-e.
PyTorch version: 2.0.0+cu117
specifically 117?
from shap-e.
by the way, any chance to run this on 8GB VRAM??
Maybe lowering the batch size will help, eg. batch_size = 1
?
from shap-e.
@Natotela in my case I used cu118
maybe higher versions will also work, but I wanted to stick to the documentation guide
from shap-e.
Related Issues (20)
- How to control number of 3D model faces? HOT 3
- Conditioning on text AND image at the same time?
- ModuleNotFoundError: No module named 'torch' HOT 1
- RuntimeError: Not compiled with GPU support
- βStrβ object has no attribute device
- RuntimeError in sample_image_to_3d.ipnb HOT 2
- Encoder can only fit 1 obj?
- need setup.py adding pytorch3d by default installation HOT 2
- How to render images with white background? HOT 1
- When will Shap-e be added to Openai's API?
- how to create obj(not per-vertex colored) legacy and material (mtl) file and texture map files from the obj?? HOT 1
- Extremely weird bug like easter egg with the very prompt "apple"
- RuntimeError: Not compiled with GPU support
- Issue on image-3D:takes very long time and big memory sometimes
- The angles and size of the generated image-3d point cloud
- encode_model throws output file error HOT 2
- Beu
- Generate point cloud
- How to calculate multiview point clouds and how to implement "Patch emb"?
- 3d HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π 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. πππ
-
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 β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from shap-e.