python-3.x - pytorch 运行 : RuntimeError: Expected all tensors to be on the same device, 但至少找到两个设备，cuda:0 和 cpu

Question

当我运行 python 代码时，第 44 行出现运行时错误:RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!

    42  feats = self.node_features[self.train_mask]
    43  labels = self.node_labels[train_mask]

    44  A = torch.mm(feats.t(), feats) + 1e-05 * torch.eye(feats.size(1))

    45  labels_one_hot = torch.zeros((feats.size(0), self.n_classes))

谁知道原因可以帮我解决一下吗!谢谢!

Answer 1

张量 torch.eye(...) 似乎在 CPU 上。您需要将其传递为 -

44  A = torch.mm(feats.t(), feats) + 1e-05 * torch.eye(feats.size(1)).to(device='cuda')

或

44  A = torch.mm(feats.t(), feats) + 1e-05 * torch.eye(feats.size(1)).cuda()