torch.Tensor() 带有 requires_grad 参数

Question

我不能将 torch.Tensor() 与 requires_grad 参数一起使用（手电筒版本：0.4.1）

没有requires_grad：

x = torch.Tensor([[.5, .3, 2.1]])
print(x)
> tensor([[0.5000, 0.3000, 2.1000]])

with requires_grad=True 或 requires_grad=False :

x = torch.Tensor([[.5, .3, 2.1]], requires_grad=False)
print(x)
Traceback (most recent call last):
  File "D:/_P/dev/ai/pytorch/notes/tensor01.py", line 4, in <module>
    x = torch.Tensor([[.5, .3, 2.1]], requires_grad=False)
TypeError: new() received an invalid combination of arguments - got (list, requires_grad=bool), but expected one of:
 * (torch.device device)
 * (torch.Storage storage)
 * (Tensor other)
 * (tuple of ints size, torch.device device)
      didn't match because some of the keywords were incorrect: requires_grad
 * (object data, torch.device device)
      didn't match because some of the keywords were incorrect: requires_grad

Answer 1

您正在使用不带 requires_grad 标志的 torch.Tensor class 构造函数创建张量 x。相反，您想使用 torch.tensor()（小写 't'）方法

x = torch.tensor([[.5, .3, 2.1]], requires_grad=False)

编辑：向文档添加 link：torch.Tensor

torch.Tensor() 带有 requires_grad 参数

torch.Tensor() with requires_grad parameter

python

pytorch

tensor