RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0

成功解决：RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cuda:1! (when checking argument for argument index in method wrapper__index_select)，报错问题。

问题原因：模型训练时，数据不在同一块GPU上
解决方案：在模型训练的代码最前面加上下面的代码即可

import os
# 指定使用一块GPU，[0,1,2,3]下面是只选择使用1号GPU
os.environ["CUDA_VISIBLE_DEVICES"] = "1"