参考链接: sort(dim=-1, descending=False) -> (Tensor, LongTensor)
参考链接: torch.sort(input, dim=-1, descending=False, out=None) -> (Tensor, LongTensor)
代码实验展示:
Microsoft Windows [版本 10.0.18363.1256]
(c) 2019 Microsoft Corporation。保留所有权利。C:\Users\chenxuqi>conda activate ssd4pytorch1_2_0(ssd4pytorch1_2_0) C:\Users\chenxuqi>python
Python 3.7.7 (default, May 6 2020, 11:45:54) [MSC v.1916 64 bit (AMD64)] :: Anaconda, Inc. on win32
Type "help", "copyright", "credits" or "license" for more information.
>>> import torch
>>> torch.manual_seed(seed=20200910)
<torch._C.Generator object at 0x00000144A347D330>
>>>
>>>
>>> x &#61; torch.randn(3, 4)
>>> x
tensor([[ 0.2824, -0.3715, 0.9088, -1.7601],[-0.1806, 2.0937, 1.0406, -1.7651],[ 1.1216, 0.8440, 0.1783, 0.6859]])
>>>
>>> sorted, indices &#61; torch.sort(x)
>>> sorted
tensor([[-1.7601, -0.3715, 0.2824, 0.9088],[-1.7651, -0.1806, 1.0406, 2.0937],[ 0.1783, 0.6859, 0.8440, 1.1216]])
>>> indices
tensor([[3, 1, 0, 2],[3, 0, 2, 1],[2, 3, 1, 0]])
>>>
>>>
>>>
>>>
>>> sorted, indices &#61; torch.sort(x, 0)
>>> sorted
tensor([[-0.1806, -0.3715, 0.1783, -1.7651],[ 0.2824, 0.8440, 0.9088, -1.7601],[ 1.1216, 2.0937, 1.0406, 0.6859]])
>>> indices
tensor([[1, 0, 2, 1],[0, 2, 0, 0],[2, 1, 1, 2]])
>>> x
tensor([[ 0.2824, -0.3715, 0.9088, -1.7601],[-0.1806, 2.0937, 1.0406, -1.7651],[ 1.1216, 0.8440, 0.1783, 0.6859]])
>>>
>>>
>>>