Autograd：自动求导

最新推荐文章于 2022-11-10 18:07:08 发布

Mason_Luo_19

最新推荐文章于 2022-11-10 18:07:08 发布

阅读量100

点赞数

本文链接：https://blog.csdn.net/bereze/article/details/103158365

版权

import torch
# 创建张量并设置requires_grad=True来追踪其计算历史
x = torch.ones(2, 2, requires_grad=True)
print(x)

tensor([[1., 1.],
        [1., 1.]], requires_grad=True)

y = x + 2
print(y)

tensor([[3., 3.],
        [3., 3.]], grad_fn=<AddBackward0>)

print(y.grad_fn)

<AddBackward0 object at 0x0000000007BFC688>

z = y * y * 3
out = z.mean()
print(z, out)

tensor([[27., 27.],
        [27., 27.]], grad_fn=<MulBackward0>) tensor(27., grad_fn=<MeanBackward1>)

# .requires_grad_(...)可以改变现有张量的requires_grad属性，默认flag为False
a = torch.randn(2, 2)
a = ((a * 3) / (a - 1))
print(a.requires_grad)

a.requires_grad_(True)
print(a.requires_grad)

b = (a * a).sum()
print(b.grad_fn)

False
True
<SumBackward0 object at 0x0000000007BEBFC8>

x1 = torch.ones(2,2,requires_grad=True)
z1 = 3 * (x1 + 2) * (x1 + 2)
out = z1.mean()
# z1 = 3(x1+2)^2, out = mean(z1)
print("x1 = ", x1)
print("z1 = ", z1)
# out是一个纯量(scalar)，out.backward()相当于out.backward(torch,tensor(1))
out.backward()
# x.grad 梯度d(out)/dx
print(x1.grad)
# 清零
x1.grad.data.zero_()

x1 =  tensor([[1., 1.],
        [1., 1.]], requires_grad=True)
z1 =  tensor([[27., 27.],
        [27., 27.]], grad_fn=<MulBackward0>)
tensor([[4.5000, 4.5000],
        [4.5000, 4.5000]])





tensor([[0., 0.],
        [0., 0.]])

x = torch.randn(3, requires_grad=True)
y = x * 2
while y.data.norm() < 1000: # .data.norm() 张量L2范数
    y = y * 2
print("y =",y)

gradients = torch.tensor([0.1, 1.0, 0.0001], dtype=torch.float)
y.backward(gradients)
print("grad =", x.grad)

y = tensor([1203.4269, 1136.8713,  854.0352], grad_fn=<MulBackward0>)
grad = tensor([2.0480e+02, 2.0480e+03, 2.0480e-01])

print(x.requires_grad)
print((x ** 2).requires_grad)
# 将变量包裹在with torch.no_grad()中，可以暂时屏蔽autograd计算
with torch.no_grad():
    print((x ** 2).requires_grad)
print((x ** 2).requires_grad)