PyTorch | torch.randperm()使用方法

公众号【计算机视觉联盟】后台回复【PyTorch】可以获得PyTorch学习教程pdf版

返回一个0~n-1的数组，随机打散的

t = torch.randperm(8)

结果：
tensor([5, 4, 2, 6, 7, 3, 1, 0])

看一下官方提示内容：

torch @overload def randperm(n: int,
             *,
             generator: Generator,
             out: Optional[Tensor] = None,
             dtype: Optional[dtype] = None,
             layout: layout = strided,
             device: Union[device, str, None] = None,
             requires_grad: bool = False) -> Tensor
Possible types:
• (n: int, Any, out: Optional[Tensor], dtype: Optional[dtype], layout: layout, device: Union[device, str, None], requires_grad: bool) -> Tensor
• (n: int, Any, generator: Generator, out: Optional[Tensor], dtype: Optional[dtype], layout: layout, device: Union[device, str, None], requires_grad: bool) -> Tensor
  < Python 3.7 (pytorch) >

torch.randperm(n, out=None, dtype=torch.int64, layout=torch.strided, device=None, requires_grad=False)