解决RuntimeError: Expected all tensors to be on the same device, but found at least two devices,

目录

1.错误：RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!

2.错误：Tensor for argument #2 ‘mat1’ is on CPU, but expected it to be on GPU (while checking arguments for addmm)

---

1.错误：RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!

原因：参与运算的两个或多个变量，有的在CPU上，有的在GPU上

解决：

1. 首先找到报错的行，看看计算时都用到哪些变量或者数据，然后在调试模式下使用.is_cuda这个属性去查看到底哪些是在GPU上，哪些是在CPU上，然后把它们统一都放在CPU，或者统一放在GPU上就可以。
2. 如果增加了变量，需要将新增加的变量也搬到GPU上去

g.ndata['norm'] = norm.unsqueeze(1)
g = g.to(device)

2.错误：Tensor for argument #2 ‘mat1’ is on CPU, but expected it to be on GPU (while checking arguments for addmm)

为了使模型在GPU上进行计算，需要将变量和模型都增加.to(device)，都搬到GPU上去即可

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

g = g.to(device)

model=model.to(device)