有numpy和torch兩種類型的數據
z = mean.clone().detach() + eps * torch.exp(logstd)
源代碼這邊報錯了，修改如下
eps = eps.cuda() z = mean.cuda()+ eps * torch.exp(logstd).cuda()
就是把和numpy有關的，比如reshape什么的后面加上cuda()
#報錯記錄#RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!
免責聲明！
本站轉載的文章為個人學習借鑒使用，本站對版權不負任何法律責任。如果侵犯了您的隱私權益，請聯系本站郵箱yoyou2525@163.com刪除。
猜您在找
【深度學習】RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!
張量與數組運算報錯(Use Tensor.cpu() to copy the tensor to host memory first;RuntimeError: Expected all tensors to be on the same device)
#報錯記錄#RuntimeError: Expected tensor for 'out' to have the same device as tensor for argument #2 'mat1'; but device 1 does not equal 0 (while checking arguments for addmm)
【E-14-Pytorch】RuntimeError: Expected object of device type cuda but got device type cpu for argument #2 'mat1' in call to _th_addmm
[報錯]-RuntimeError: Input type (torch.cuda.HalfTensor) and weight type (torch.cuda.FloatTensor) should be the same
RuntimeError: Expected object of backend CUDA but got backend CPU for argument #4 'mat1'
RuntimeError: Expected object of type torch.cuda.FloatTensor but found type torch.FloatTensor for ar
RuntimeError: invalid argument 0: Tensors must have same number of dimensions: got 1 and 2 at /opt/conda/conda-
RuntimeError: CUDA error: invalid device ordinal
Pytoch的nn.CrossEntropyLoss 報錯 RuntimeError: expected scalar type Long but found Float