.backward() 之后 pytorch grad 为 None

pytorch grad is None after .backward()(.backward() 之后 pytorch grad 为 None)

问题描述

我刚刚在 Python 3.7.2 (macOS) 上安装了 torch-1.0.0，并尝试了 教程，但是下面的代码:

I just installed torch-1.0.0 on Python 3.7.2 (macOS), and trying the tutorial, but the following code:

import torch
x = torch.ones(2, 2, requires_grad=True)
y = x + 2
z = y * y * 3
out = z.mean()
out.backward()
print(out.grad)

打印 None 这不是预期的.

prints None which is not what's expected.

有什么问题吗?

推荐答案

这是预期的结果.

.backward 仅在叶节点中累积梯度.out 不是叶节点，因此 grad 是 None.

.backward accumulate gradient only in the leaf nodes. out is not a leaf node, hence grad is None.

autograd.backward 也做同样的事情

autograd.grad 可用于查找任何张量 w.r.t 到任何张量的梯度.所以如果你做 autograd.grad (out, out) 你会得到 (tensor(1.),) 作为输出，这是预期的.

autograd.grad can be used to find the gradient of any tensor w.r.t to any tensor. So if you do autograd.grad (out, out) you get (tensor(1.),) as output which is as expected.

参考:

• Tensor.backward (https://pytorch.org/docs/stable/autograd.html#torch.Tensor.backward)
• autograd.backward (https://pytorch.org/docs/stable/autograd.html#torch.autograd.backward)
• autograd.grad (https://pytorch.org/docs/stable/autograd.html#torch.autograd.grad)

这篇关于.backward() 之后 pytorch grad 为 None的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持编程学习网！