代码报错

[luckyonetwo]

你好，非常感谢你提供的代码，请问一下，报错出现这个问题怎么解决呢：RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu

[ankandrew]

Hi @luckyonetwo! If you are training with gpu, then you will need to move the loss to the gpu, so it'd be something like:

from ols import OnlineLabelSmoothing
import torch

k = 4  # Number of classes
b = 32  # Batch size
criterion = OnlineLabelSmoothing(alpha=0.5, n_classes=k, smoothing=0.1).cuda()

Let me know if this didn't solve the issue and need any help