PyTorch-view, squeeze, unsqueeze, cat, stack, size

In 3-dimension tensor, count how many items are there.

 

0th dimension

[ [ [ , ] ] ]

[] = 3

 

1st dimension

[ [ [ , ] ] ]

[] = 1

 

2nd dimension

[ [ [ , ] ] ]

[] = 2

 

tensor([[[0, 1]],
        [[1, 1]],
        [[2, 1]]])
        
torch.Size([3, 1, 2])

 

• FloatTensor

Create matrix.

torch.FloatTensor([[1.,2.],[3.,4.],[5.,6.]])

>>>

tensor([[1., 2.],
        [3., 4.],
        [5., 6.]])

 

• view

Same function as reshape in numpy.

-1 : It means I am not sure so I will let pytorch to decide the dimension.

torch.FloatTensor([[[1.,2.],[3.,4.]],[[5.,6.],[7.,8.]]])

>>>

tensor([[[1., 2.],
         [3., 4.]],

        [[5., 6.],
         [7., 8.]]])
         
t.view([-1,2])

>>>

tensor([[1., 2.],
        [3., 4.],
        [5., 6.],
        [7., 8.]])

a=torch.randn(1,2,3,4)
a
>>>

tensor([[[[ 0.3861, -0.2761, -2.0326,  0.1494],
          [ 0.4762, -0.3741,  1.5705, -0.7584],
          [ 0.4935, -0.9561, -0.5429,  2.1391]],

         [[ 0.1052, -0.4533, -1.4188,  1.7282],
          [-0.1203, -1.3732,  0.4870, -1.5323],
          [-0.6002, -0.1653,  2.3912, -2.3870]]]])
          
a.view(1,3,2,4)
>>>

tensor([[[[ 0.3861, -0.2761, -2.0326,  0.1494],
          [ 0.4762, -0.3741,  1.5705, -0.7584]],

         [[ 0.4935, -0.9561, -0.5429,  2.1391],
          [ 0.1052, -0.4533, -1.4188,  1.7282]],

         [[-0.1203, -1.3732,  0.4870, -1.5323],
          [-0.6002, -0.1653,  2.3912, -2.3870]]]])

• squeeze

Remove 1-dimension from tensor.

ft=torch.FloatTensor([[0],[1],[2]])
print(ft)
print(ft.shape)

>>>

tensor([[0.],
        [1.],
        [2.]])
torch.Size([3, 1])

print(ft.squeeze())
print(ft.squeeze().shape)

>>>

tensor([0., 1., 2.])
torch.Size([3])

 

• unsqueeze

Add 1-dimension.

ft_1=ft.squeeze()
ft_1.unsqueeze(0)

>>>

tensor([[0., 1., 2.]])

 

• cat

Concatenate.

x=torch.LongTensor([[1,2],[3,4]]).float()
y=torch.LongTensor([[5,6],[7,8]]).float()

torch.cat([x,y])

>>>

tensor([[1., 2.],
        [3., 4.],
        [5., 6.],
        [7., 8.]])
        
torch.cat([x,y],dim=0)

>>>

tensor([[1., 2.],
        [3., 4.],
        [5., 6.],
        [7., 8.]])
        
torch.cat([x,y],dim=1)

>>>

tensor([[1., 2., 5., 6.],
        [3., 4., 7., 8.]])

 

• stack

x = torch.FloatTensor([1, 4])
y = torch.FloatTensor([2, 5])
z = torch.FloatTensor([3, 6])

torch.stack([x, y, z])

>>>

tensor([[1., 4.],
        [2., 5.],
        [3., 6.]])

Same as below.

torch.cat([x.unsqueeze(0), y.unsqueeze(0)],dim=0)

>>>

tensor([[[1., 2.],
         [3., 4.]],

        [[5., 6.],
         [7., 8.]]])

 

• size

t = torch.FloatTensor([0., 1., 2., 3., 4., 5., 6.])
print(t)
print(t.size(0))
print(t.size(dim=0))

>>>

tensor([0., 1., 2., 3., 4., 5., 6.])
7
7