CODEWITHSUNDEEP
pythonpytorchsizetensor
Suho Cho
Suho Cho

Reputation: 585

How to use `stack()` in PyTorch?

How do I use torch.stack() to stack two tensors with shapes a.shape = (2, 3, 4) and b.shape = (2, 3) without an in-place operation?

Upvotes: 30

Views: 68437

Answers (3)

pourya
pourya

Reputation: 67

suppose you have two tensors a, b which are equal in dimensions i.e a ( A, B, C) so b (A, B , C) an example

a=torch.randn(2,3,4)
b=torch.randn(2,3,4)
print(a.size())  # 2, 3, 4
print(b.size()) # 2, 3, 4

f=torch.stack([a, b], dim=2)  # 2, 3, 2, 4
f

it wont act if they wouldn't be the same dim. Be careful!!

Upvotes: 5

gil.fernandes
gil.fernandes

Reputation: 14641

Using pytorch 1.2 or 1.4 arjoonn's answer did not work for me.

Instead of torch.stack I have used torch.cat with pytorch 1.2 and 1.4:

>>> 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])

If you want to use torch.stack the dimensions of the tensors have to be the same:

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

Here is another example:

>>> t = torch.tensor([1, 1, 2])
>>> stacked = torch.stack([t, t, t], dim=0)
>>> t.shape, stacked.shape, stacked

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

With stack you have the dim parameter which lets you specify on which dimension you stack the tensors with equal dimensions.

Upvotes: 22

arjoonn
arjoonn

Reputation: 988

Stacking requires same number of dimensions. One way would be to unsqueeze and stack. For 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

Upvotes: 37

Related Questions