Torch.stack

Torch.stack example

a.size()  # 2, 3, 4
b.size()  # 2, 3
b = torch.unsqueeze(b, dim=2)  # 2, 3, 1
# torch.unsqueeze(b, dim=-1) does the same thing

torch.stack([a, b], dim=2)  # 2, 3, 5

Source: newbedev.com

Torch.stack example

>>> a = torch.randn([2, 3, 4])
>>> b = torch.randn([2, 3, 4])
>>> torch.stack([a, b]).shape
torch.Size([2, 2, 3, 4])

Source: newbedev.com

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.stack

> torch.stack(
    (t1,t2,t3)
    ,dim=0
)
tensor([[1, 1, 1],
        [2, 2, 2],
        [3, 3, 3]])

Source: deeplizard.com

Torch.stack example

>>> import torch
>>> a = torch.randn([2, 3, 4])
>>> b = torch.randn([2, 3])
>>> b = b.unsqueeze(dim=2)
>>> b.shape
torch.Size([2, 3, 1])
>>> torch.cat([a, b], dim=2).shape
torch.Size([2, 3, 5])

Source: newbedev.com

Similar codes

1 vote151 views1 answer
How to leave some parameters in python and let the value be anything
Python
1 vote147 views3 answers
Dataframe groupby to dictionary
Python
5 votes161 views4 answers
Pathlib get extension
Python
0 vote149 views1 answer
# Import KNeighborsClassifier from sklearn.neighbors
Python
1 vote172 views1 answer
Remove duplicate rows in csv file python
Python
2 votes152 views2 answers
For j in range(1,10,-1):
Python
16 votes142 views4 answers
Python check list contains another list
Python
1 vote201 views1 answer
Django return only part of string
Python Django
0 vote139 views1 answer
Tensorfow list devices
Python
10 votes132 views3 answers
Python reduce
Python