Comments (2)
Hi @SunHaozhe
Unfortunately, I can not test the library with Pytorch 1.8 on CUDA at the moment.
However, looking at your code, I think you can fix the runtime error in the title by using for example
gnn.init.generalized_he_init(conv.weights.data, conv.basisexpansion)
instead of
gnn.init.generalized_he_init(conv.weights, conv.basisexpansion)
The problem is that the weight initialization methods operate in-place (like PyTorch's ones).
I see that PyTorch uses with torch.no_grad()
inside the init methods, so maybe I should do the same.
I need to think a bit more about this to make sure it wouldn't cause other problems, but in the meantime you can use the trick above to solve your issue.
Regarding the second issue, I ran the script you mentioned on a machine without GPU (I used my own conda environment with PyTorch 1.8) but I didn't encounter any issue.
However, note that generate_synthetic_data
assumes you have a GPU since it explicitly uses .to('cuda')
.
That means that you need to remove that stametement from your code if you want to run it on CPU.
Let me know if this solves your issues
Best,
Gabriele
from e2cnn.
Thanks a lot for your reply! I indeed solved the issue by switching to a machine with CUDA and the correct PyTorch version. This issue can be helpful for everyone who encounter the same problem (if any) :)
from e2cnn.
Related Issues (20)
- wrapping pytorch operations - grid_sample HOT 4
- Import Error with Torch 1.9.0+cu111 HOT 2
- equivariant Transformer HOT 5
- ZeroPad2D on GeometricTensor
- Cannot pass weights of R2Conv as a positional argument HOT 2
- Counting FLOPs for e2cnn HOT 1
- equivariance in C8 space HOT 1
- Module export HOT 3
- About the equivalence of wide_resnet HOT 5
- Need a size parameter for e2cnn.R2Upsampling Class HOT 1
- about attribute R2conv.filter HOT 2
- Learning of kernels HOT 2
- O(2) group, irreps, and PyTorch DDP. HOT 2
- checking equivariance for the angles that are not 90n HOT 2
- about to set special rotation equivariant HOT 2
- Cannot import name container_abcs in python 3.6 version (e2cnn_py36)
- shriking size of output image
- Use of np.float and np.int etc
- Difference between trivial output type and regular output type with group pooling HOT 1
- Export Linear 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 e2cnn.