criterion = nn.MSELoss()
criterion(a, b)
这是a的dtype=torch.float，b的dtype=torch.int64
因此，都改成float
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
"host_softmax" not implemented for 'Long'
解决RuntimeError: CUDA error: out of memory
RuntimeError: cuda runtime error (30) : unknown errorr
RuntimeError: CUDA error: device-side assert triggered的解决
import logging报错raise notimplementederror 'emit must be implemented ' ^
RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is Fal
ubuntu查看并杀死自己之前运行的进程解决办法RuntimeError: CUDA error: out of memory
RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same
PyTorch错误解决RuntimeError: Attempting to deserialize object on a CUDA device but torch.cu
RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same