'Colab Session Crashes on importing torch_geometric.data
My colab session always crashes while trying to import torch_geometric.data module. For reference, the code I am writing is as follows:
import torch
def format_pytorch_version(version):
return version.split('+')[0]
TORCH_version = torch.__version__
TORCH = format_pytorch_version(TORCH_version)
def format_cuda_version(version):
return 'cu' + version.replace('.', '')
CUDA_version = torch.version.cuda
CUDA = format_cuda_version(CUDA_version)
!pip install torch-scatter -f https://pytorch-geometric.com/whl/torch-{TORCH}+{CUDA}.html
!pip install torch-sparse -f https://pytorch-geometric.com/whl/torch-{TORCH}+{CUDA}.html
!pip install torch-cluster -f https://pytorch-geometric.com/whl/torch-{TORCH}+{CUDA}.html
!pip install torch-spline-conv -f https://pytorch-geometric.com/whl/torch-{TORCH}+{CUDA}.html
!pip install torch-geometric
!pip install torch_geometric
from torch_geometric.data import Data
When the execution reaches the lats line, the colab session crashes, I have tried switching to GPU and TPU as well, but nothing happens.
The logs shows this:
WARNING:root:kernel fc8fda2d-f1ce-4808-b78f-a18a55132346 restarted
Solution 1:[1]
Got same issue this week. Downgrading PyTorch to the same version as pytorch_geometric seems to have solved the issue.
!pip install torch==1.10.0+cu111 torchvision==0.11.0+cu111 torchaudio==0.10.0 -f https://download.pytorch.org/whl/torch_stable.html
Sources
This article follows the attribution requirements of Stack Overflow and is licensed under CC BY-SA 3.0.
Source: Stack Overflow
| Solution | Source |
|---|---|
| Solution 1 |
