RuntimeError: expected backend CPU and dtype Float but got backend CPU and dtype Long

源代码

import torch

x = torch.tensor([5])
#初始化权重参数w,偏移量b，设置自动求导
w = torch.randn(1,requires_grad=True)
b = torch.randn(1,requires_grad=True)
# 实现前向传播
y = torch.mul(w,x)
z = torch.add(y,b)
print("x,w,b的require_grad属性分别为{},{},{}".format(x.requires_grad,w.requires_grad,b.requires_grad))

报错代码：第8行  y = torch.mul(w,x)   

x的类型是int64,  w的类型是float

解决方法：把x变成float：

x = torch.tensor([5]).float()