torch.Tensor.size()方法的使用举例

参考链接: size()

该方法返回的是当前张量的形状,返回值是元组tuple的一个子类.
代码实验举例:

(base) PS C:\Users\chenxuqi> python
Python 3.7.4 (default, Aug  9 2019, 18:34:13) [MSC v.1915 64 bit (AMD64)] :: Anaconda, Inc. on win32
Type "help", "copyright", "credits" or "license" for more information.
>>> import torch
>>> a = torch.ones(2,3,4)
>>> a
tensor([[[1., 1., 1., 1.],
         [1., 1., 1., 1.],
         [1., 1., 1., 1.]],

        [[1., 1., 1., 1.],
         [1., 1., 1., 1.],
         [1., 1., 1., 1.]]])
>>> a.size
<built-in method size of Tensor object at 0x000001D0D5CAE368>
>>>
>>> a.size()
torch.Size([2, 3, 4])
>>>
>>> a.size(0)
2
>>> a.size()[0]
2
>>>
>>>
>>> a = torch.ones(2,3,4,5,6,7,8,9)
>>> a.shape
torch.Size([2, 3, 4, 5, 6, 7, 8, 9])
>>> a.size()
torch.Size([2, 3, 4, 5, 6, 7, 8, 9])
>>> a.size(0)
2
>>> a.size(7)
9
>>> a.size()[0]
2
>>> a.size()[7]
9
>>> a.size(4)
6
>>> a.size()[4]
6
>>>
>>>
>>> a.size()[:]
torch.Size([2, 3, 4, 5, 6, 7, 8, 9])
>>>
>>> a.size()[4:]
torch.Size([6, 7, 8, 9])
>>>
>>>
>>>
>>>