pyg Symbol not found: __ZN2at8internal13_parallel_runExxxRKNSt3__18functionIFvxxmEE

今天在跑pyg的gcn的例子的时候出现了下面的错误：

 import torch_geometric.data
  File "/Users/../anaconda3/envs/yolo/lib/python3.8/site-packages/torch_geometric/data/__init__.py", line 1, in <module>
    from .data import Data
  File "/Users/../anaconda3/envs/yolo/lib/python3.8/site-packages/torch_geometric/data/data.py", line 9, in <module>
    from torch_sparse import SparseTensor
  File "/Users/../anaconda3/envs/yolo/lib/python3.8/site-packages/torch_sparse/__init__.py", line 19, in <module>
    torch.ops.load_library(spec.origin)
  File "/Users/../anaconda3/envs/yolo/lib/python3.8/site-packages/torch/_ops.py", line 110, in load_library
    ctypes.CDLL(path)
  File "/Users/../anaconda3/envs/yolo/lib/python3.8/ctypes/__init__.py", line 373, in __init__
    self._handle = _dlopen(self._name, mode)
OSError: dlopen(/Users/../anaconda3/envs/yolo/lib/python3.8/site-packages/torch_sparse/_convert_cpu.so, 6): Symbol not found: __ZN2at8internal13_parallel_runExxxRKNSt3__18functionIFvxxmEEE
  Referenced from: /Users/../anaconda3/envs/yolo/lib/python3.8/site-packages/torch_sparse/_convert_cpu.so
  Expected in: /Users/../anaconda3/envs/yolo/lib/python3.8/site-packages/torch/lib/libtorch_cpu.dylib
 in /Users/../anaconda3/envs/yolo/lib/python3.8/site-packages/torch_sparse/_convert_cpu.so

我的gcn的例子的代码来源为：

Learning Methods on Graphs

import torch
import torch.nn.functional as F
from torch_geometric.nn import GCNConv

class GCN(torch.nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = GCNConv(dataset.num_node_features, 16)
        self.conv2 = GCNConv(16, dataset.num_classes)

    def forward(self, data):
        x, edge_index = data.x, data.edge_index

        x = self.conv1(x, edge_index)
        x = F.relu(x)
        x = F.dropout(x, training=self.training)
        x = self.conv2(x, edge_index)

        return F.log_softmax(x, dim=1)

from torch_geometric.datasets import Planetoid

dataset = Planetoid(root='./Cora', name='Cora')
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = GCN().to(device)
data = dataset[0].to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=0.01, weight_decay=5e-4)

model.train()
for epoch in range(200):
    optimizer.zero_grad()
    out = model(data)
    loss = F.nll_loss(out[data.train_mask], data.y[data.train_mask])
    loss.backward()
    optimizer.step()

model.eval()
pred = model(data).argmax(dim=1)
correct = (pred[data.test_mask] == data.y[data.test_mask]).sum()
acc = int(correct) / int(data.test_mask.sum())
print(f'Accuracy: {acc:.4f}')

解决方法

我用conda换了一个新的环境，然后执行下面的命令：

conda install pytorch torchvision torchaudio cpuonly -c pytorch
conda install pyg -c pyg

然后就可以运行了

参考文献

Pytorch Geometric 安装中的问题