Use expand in pytorch version 0.2

1

Hi Guys,

I would like to use expand to expand tensors. For example, I would like to expand tensor A with size 256x15 to size 256x15x24. So I use A.expand(256, 15, 24). It works when I use pytorch 0.1.12. However, I get the following error when I use this in pytorch 0.2.

Traceback (most recent call last):
File “”, line 1, in
RuntimeError: The expanded size of the tensor (24) must match the existing size (15) at non-singleton dimension 2. at /opt/conda/conda-bld/pytorch_1503963423183/work/torch/lib/TH/generic/THTensor.c:308

Any help on this issue?

Thanks in advance.

1 Like
2

The problem is that you are adding a dimension at the end. expand now only adds new dimensions up front (http://pytorch.org/docs/master/tensors.html#torch.Tensor.expand), being consistent with numpy’s broadcasting rules. What you can do is to first unsqueeze to add a dimension, and then expand. (At least) two ways to do this:

  1. Numpy-style broadcasting: A[:, :, None].expand(256, 15, 24)
  2. Explicit unsqueeze: A.unsqueeze(-1).expand(256, 15, 24)
1 Like
3

This might help you:

x = torch.randn(256, 15)
x.unsqueeze_(-1)
x.expand(256, 15, 24)
1 Like
4

Thanks for the solution!

5

Thanks for the quick response!