原因：变量没有加cuda
data=data.cuda()
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 scalar type Float but got scalar type Double for argument #4 'mat1'的解决方法
RuntimeError: expected backend CPU and dtype Double but got backend CPU and dtype Float
#报错记录#RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!
【深度学习】RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!
Expected 1 arguments, but got 0. Did you forget to include 'void' in your type argument to 'Promise'?
Python2.7 在使用BSTestRunner.py时报错TypeError: unicode argument expected, got 'str'
RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False.
Invalid prop: type check failed for prop "XXX". Expected String, got Object.
【Vue-bug】[Vue warn]:Invalid prop: type check failed for prop “data“.Expected Array,got Object
解决：RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. Got 544 and 1935 in dimension 2 at ../aten/src/TH/generic/THTensor.cpp:711