火炬模块的某些成员不会被移到gpa,即使型号.to(设备)被调用

import torch
import torch.nn as nn

class model(nn.Module):
    def __init__(self):
        super(model,self).__init__()
        self.mat = torch.randn(2,2)

    def forward(self,x):
        print('self.mat.device is',self.mat.device)
        x = torch.mv(self.mat,x)
        return x

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

x = torch.tensor([2.,1.])
x = x.to(device)

m(x)

输出是

self.mat.device is cpu

就在那之后

Traceback (most recent call last):
  File "Z:\cudatest.py", line 21, in <module>
    print(m(x))
  File "E:\Python37\lib\site-packages\torch\nn\modules\module.py", line 532, in __call__
    result = self.forward(*input, **kwargs)
  File "Z:\cudatest.py", line 11, in forward
    x = torch.mv(self.mat,x)
RuntimeError: Expected object of device type cuda but got device type cpu for argument #1 'self' in call to _th_mv

如果我设置代码,代码可以正常工作 device = torch.device('cpu') . 看来问题是 model.mat 即使之后也不会移动到GPU m.to(device)

1. 即使这个特定的例子可以用 self.mat = nn.Linear(2,2) 和 x = self.mat(x) 相反,在我最初的程序中,我需要一个临时张量来存储一些数据 forward() 这在一些算法中也有使用。如何构造这样一个张量并在调用时发送给GPU m、 至(设备)

2. 事先不知道计算机是否有GPU。因此,写作 self.mat = self.mat.cuda()