Torch.unsqueeze

Pytorch squeeze

x = torch.zeros(2, 1, 2, 1, 2)
x.size()
>>> torch.Size([2, 1, 2, 1, 2])

y = torch.squeeze(x) # remove 1
y.size()
>>> torch.Size([2, 2, 2])

y = torch.squeeze(x, 0)
y.size()
>>> torch.Size([2, 1, 2, 1, 2])

y = torch.squeeze(x, 1)
y.size()
>>> torch.Size([2, 2, 1, 2])

Source: pytorch.org

Torch.unsqueeze

a = torch.randn(4, 4, 4)
>>> torch.unsqueeze(a, 0).size()
torch.Size([1, 4, 4, 4])

>>> torch.unsqueeze(a, 1).size()
torch.Size([4, 1, 4, 4])

>>> torch.unsqueeze(a, 2).size()
torch.Size([4, 4, 1, 4])

>>> torch.unsqueeze(a, 3).size()
torch.Size([4, 4, 4, 1])

Source: linuxpip.org

Similar codes

2 votes291 views1 answer
Python merge strings in columns
Python
0 vote359 views1 answer
Django today date in template
Python Django
0 vote313 views1 answer
Temp variable python
Python
0 vote340 views1 answer
The module in NAME could not be imported: django.contrib.user_auth.password_validation.UserAttributeSimilarityValidator. Check your AUTH_PASSWORD_VALI
Python Django
0 vote327 views1 answer
Comment voir les requêtes SQL brutes exécutées par Django?
Python Django
28 votes308 views3 answers
Datetime one month ago python
Python
1 vote293 views1 answer
Python change name of the imported function
Python
0 vote286 views1 answer
Django get latest object
Python
0 vote276 views1 answer
TypeError at /admin/auth/user/
Python
0 vote304 views1 answer
Replace nan in pandas column with mode and printing it
Python