Pytorch 显示“NoneType”对象没有属性“zero_”向后错误

Question

嗨，我开始学习 pytorch。当我尝试重置权重和偏差梯度时，我得到了 27 b.grad.zero_()

AttributeError：“NoneType”对象没有属性“zero_”错误。

input = torch.tensor([73,67,43,91,88,64,87,134,58,102,43,37,69,96,70],dtype=torch.float32)
inputnew = input.reshape(5,3)
target = torch.tensor([56,70,81,101,119,133,22,37,103,119])
targetnew = target.reshape(5,2)

w = torch.randn(2,3,requires_grad = True)
b = torch.randn(2,requires_grad = True)

def model(x):
       return x @ w.t()+ b
islem= model(inputnew)
def fix(real,pred):
    diff = real-pred
    return torch.sum((diff*diff)/diff.numel())
loss = fix(targetnew,islem)

for i in range(100):
    islem = model(inputnew)
    loss = fix(targetnew,islem)
    loss.backward()
    with torch.no_grad():
            w=w- w.grad*1e-5 
            b=b-b.grad*1e-5
            w.grad.zero_()
            b.grad.zero_()

我该如何解决？谢谢

Answer 1

w = w - w.grad * 1e-5

创建一个新张量并将其分配给

w

。这会破坏链接，导致

w.grad

设置为

None

。

要修复它，您应该将张量更新为

w -= w.grad * 1e-5

:

    with torch.no_grad():
        w -= w.grad * 1e-5
        b -= b.grad * 1e-5
        w.grad.zero_()
        b.grad.zero_()