criterion = nn.MSELoss()
criterion(a, b)
這是a的dtype=torch.float，b的dtype=torch.int64
因此，都改成float
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
RuntimeError: reciprocal is not implemented for type torch.cuda.LongTensor
"host_softmax" not implemented for 'Long'
存在空閑CUDA前提下報錯：RuntimeError: CUDA error: out of memory
[報錯]-RuntimeError: Input type (torch.cuda.HalfTensor) and weight type (torch.cuda.FloatTensor) should be the same
Pytoch的nn.CrossEntropyLoss 報錯 RuntimeError: expected scalar type Long but found Float
#報錯記錄#RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!
pytorch遇到的問題：RuntimeError: randperm is only implemented for CPU
*** RuntimeError: CUDA error: out of memory.
RuntimeError: CUDA error: invalid device ordinal
RuntimeError: CUDA error: an illegal memory access was encountered