https://www.jianshu.com/p/0be7a375bdbe
https://blog.csdn.net/qq_38410428/article/details/82973895
计算中有的参数为cuda型，有的参数却是cpu型，就会遇到这样的错误。
解决办法：
该加.cuda()的加上，不该用.cpu()的地方去掉它。
免责声明！
本站转载的文章为个人学习借鉴使用，本站对版权不负任何法律责任。如果侵犯了您的隐私权益，请联系本站邮箱yoyou2525@163.com删除。
猜您在找
RuntimeError: Expected object of type torch.cuda.FloatTensor but found type torch.FloatTensor for ar
Pytorch出现RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor)
[报错]-RuntimeError: Input type (torch.cuda.HalfTensor) and weight type (torch.cuda.FloatTensor) should be the same
torch.cuda.FloatTensor
`TypeError: torch.mm received an invalid combination of arguments - got (torch.FloatTensor, Variable),
vue常见错误：Invalid prop: type check failed for prop "data". Expected Array, got Object
one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [3, 1280, 28, 28]], which is output 0 of LeakyReluBackward1, is at version 2;
expected "indent", got "outdent" 错误
SyntaxError: expected expression, got '<'异常错误
Expected object of backend CPU but got backend CUDA for argument #2 'weight'