RuntimeError: expected device cpu and dtype Float but got device cpu and dtype Long

prob * SCORES 报错：
RuntimeError: expected device cpu and dtype Float but got device cpu and dtype Long
其中prob和SCORES的数据及类型是：
SCORES = torch.tensor([[1, 2, 3, 4, 5]])
In [71]: prob
Out[71]: 
tensor([[0.2000, 0.2000, 0.2000, 0.2000, 0.2000],
[0.2001, 0.2002, 0.1998, 0.2001, 0.1998],
[0.2000, 0.2000, 0.2000, 0.2000, 0.2000],
...,
[0.2000, 0.2000, 0.2000, 0.2000, 0.2000],
[0.2000, 0.2000, 0.2000, 0.2000, 0.2000],
[0.1999, 0.2000, 0.2000, 0.2000, 0.2000]], grad_fn=<SoftmaxBackward>)

解决方法：
将SCORES由整数类型改为float类型：
SCORES = torch.tensor([[1., 2., 3., 4., 5.]])
或者：
SCORES = SCORES.float()