I’m trying to stack tensors with different size. But only dimension 2 is different while other dimensions are all same. Is there any way to do this?
torch.cat should work:
a = torch.randn(5, 5, 1) b = torch.randn(5, 5, 4) c = torch.cat((a, b), dim=2) print(c.shape) > torch.Size([5, 5, 5])
thanks bro, you saved me