【问题标题】:torch.Tensor() with requires_grad parameter带有 requires_grad 参数的 torch.Tensor()
【发布时间】:2018-11-08 05:15:53
【问题描述】:

我不能使用带有 requires_grad 参数的 torch.Tensor()(torch 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

【问题讨论】:

    标签: python pytorch tensor


    【解决方案1】:

    您正在使用不带 requires_grad 标志的 torch.Tensor 类构造函数创建张量 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:添加文档链接:torch.Tensor

    【讨论】:

    • 想知道为什么会有torch.tensortorch.Tensor
    猜你喜欢
    • 2021-10-15
    • 2019-01-25
    • 1970-01-01
    • 2018-11-29
    • 2020-12-26
    • 1970-01-01
    • 2016-08-08
    • 1970-01-01
    • 2017-12-08
    相关资源
    最近更新 更多