Traceback (most recent call last):
File "finetune_OAG_PF.py", line 3, in <module>
from GPT_GNN.model import *
File "/home/DYT/GPTuning/GPT-GNN/example_OAG/GPT_GNN/model.py", line 1, in <module>
from .conv import *
File "/home/DYT/GPTuning/GPT-GNN/example_OAG/GPT_GNN/conv.py", line 5, in <module>
from torch_geometric.nn import GCNConv, GATConv, RGCNConv
File "/home/chenliyi/anaconda3/envs/pygt1.5/lib/python3.6/site-packages/torch_geometric/__init__.py", line 2, in <module>
import torch_geometric.nn
File "/home/chenliyi/anaconda3/envs/pygt1.5/lib/python3.6/site-packages/torch_geometric/nn/__init__.py", line 2, in <module>
from .data_parallel import DataParallel
File "/home/chenliyi/anaconda3/envs/pygt1.5/lib/python3.6/site-packages/torch_geometric/nn/data_parallel.py", line 5, in <module>
from torch_geometric.data import Batch
File "/home/chenliyi/anaconda3/envs/pygt1.5/lib/python3.6/site-packages/torch_geometric/data/__init__.py", line 1, in <module>
from .data import Data
File "/home/chenliyi/anaconda3/envs/pygt1.5/lib/python3.6/site-packages/torch_geometric/data/data.py", line 7, in <module>
from torch_sparse import coalesce
File "/home/chenliyi/anaconda3/envs/pygt1.5/lib/python3.6/site-packages/torch_sparse/__init__.py", line 2, in <module>
from .coalesce import coalesce
File "/home/chenliyi/anaconda3/envs/pygt1.5/lib/python3.6/site-packages/torch_sparse/coalesce.py", line 2, in <module>
import torch_scatter
File "/home/chenliyi/anaconda3/envs/pygt1.5/lib/python3.6/site-packages/torch_scatter/__init__.py", line 3, in <module>
from .mul import scatter_mul
File "/home/chenliyi/anaconda3/envs/pygt1.5/lib/python3.6/site-packages/torch_scatter/mul.py", line 3, in <module>
from torch_scatter.utils.ext import get_func
File "/home/chenliyi/anaconda3/envs/pygt1.5/lib/python3.6/site-packages/torch_scatter/utils/ext.py", line 2, in <module>
import torch_scatter.scatter_cpu
ImportError: /home/chenliyi/anaconda3/envs/pygt1.5/lib/python3.6/site-packages/torch_scatter/scatter_cpu.cpython-36m-x86_64-linux-gnu.so: undefined symbol: _ZN6caffe26detail37_typeMetaDataInstance_preallocated_32E
Is there any method to fix it?
thank you!
Environment
PyG version: 1.3.2
PyTorch version: 1.5.0
OS: ubuntu18.04
Python version: 3.6.13
CUDA/cuDNN version: 10.22 7605
How you installed PyTorch and PyG (conda, pip, source): pip
Any other relevant information (e.g., version of torch-scatter): torch-scatter==1.3.2
torch-cluster==1.4.5
torch-sparse==0.4.3
torch-spline-conv==1.1.1
torch-geometric==1.3.2
😵 Describe the installation problem
When I run the code of GPT-GNN, It report that
Is there any method to fix it? thank you!
Environment
conda
,pip
, source): piptorch-scatter
): torch-scatter==1.3.2 torch-cluster==1.4.5 torch-sparse==0.4.3 torch-spline-conv==1.1.1 torch-geometric==1.3.2