I wanna find some torch function like this:
input : a = [[1,2,3,4], [5,6,7,8]], b = [[0,0,0,0],[0,0,0,0]]
output : c = [[[1,0],[2,0],[3,0],[4,0]],[[5,0],[6,0],[7,0],[8,0]]]
Does this kind of function exist in torch?
I wanna find some torch function like this:
input : a = [[1,2,3,4], [5,6,7,8]], b = [[0,0,0,0],[0,0,0,0]]
output : c = [[[1,0],[2,0],[3,0],[4,0]],[[5,0],[6,0],[7,0],[8,0]]]
Does this kind of function exist in torch?
Yes, you can use torch.stack
:
a = torch.tensor([[1,2,3,4], [5,6,7,8]])
b = torch.tensor([[0,0,0,0],[0,0,0,0]])
c = torch.tensor([[[1,0],[2,0],[3,0],[4,0]],[[5,0],[6,0],[7,0],[8,0]]])
print(c)
> tensor([[[1, 0],
[2, 0],
[3, 0],
[4, 0]],
[[5, 0],
[6, 0],
[7, 0],
[8, 0]]])
d = torch.stack((a, b), dim=2)
print(d)
> tensor([[[1, 0],
[2, 0],
[3, 0],
[4, 0]],
[[5, 0],
[6, 0],
[7, 0],
[8, 0]]])
oh, that’s exactly what I want.
thanks so much :).