I have a torch tensor of size torch.Size([1, 128, 56, 128])
1 is channel, 128 is the width, and height. 56 is the number of images.
How can I resize it to torch.Size([1, 56, 128, 128])
?
thankyou
I have a torch tensor of size torch.Size([1, 128, 56, 128])
1 is channel, 128 is the width, and height. 56 is the number of images.
How can I resize it to torch.Size([1, 56, 128, 128])
?
thankyou
You need to permute
or transpose
the tensor:
import torch
a = torch.randn(1, 128, 56, 128)
print(a.permute(0, 2, 1, 3).shape)
print(a.transpose(2, 1).shape)
torch.Size([1, 56, 128, 128])
torch.Size([1, 56, 128, 128])
thankyou, it worked!