Opening the paper…
Figure from the original question paper You have a tensor `x = torch.tensor([1, 2, 3, 4])` with shape `(4,)`. You perform the following operations: stacked_x = torch.stack([x, x, x], dim=0) stacked_y = torch.stack([x, x, x], dim=1) What are the shapes of `stacked_x` and `stacked_y` respectively? Figure from the original question paper