Is there any way to reshape tensor shape.
I ran into this problem using TensorDataset and Dataloader. I can’t use transforms here.
Any directly method without changing to numpy?
Thanks for ideas.
Is there any way to reshape tensor shape.
I ran into this problem using TensorDataset and Dataloader. I can’t use transforms here.
Any directly method without changing to numpy?
Thanks for ideas.
Hi,
Can torch.nn.functional.interpolate
this solve your issue?
Bests
Yay, thanks.
As solution i have converted
[20,784]
i.e [20,1,28,28]
to [20,1,32,32]
using interpolate as
xb = F.interpolate(xb, size=32,32) #The resize operation on tensor.