How to resize a PyTorch tensor?

Question

I have a PyTorch tensor of size (5, 1, 44, 44) (batch, channel, height, width), and I want to 'resize' it to (5, 1, 224, 224)

How can I do that? What functions should I use?

Solution

It seems like you are looking for interpolate (a function in nn.functional):

import torch.nn.functional as nnf

x = torch.rand(5, 1, 44, 44)
out = nnf.interpolate(x, size=(224, 224), mode='bicubic', align_corners=False)

If you really care about the accuracy of the interpolation, you should have a look at ResizeRight: a pytorch/numpy package that accurately deals with all sorts of "edge cases" when resizing images. This can have effect when directly merging features of different scales: inaccurate interpolation may result with misalignments.

Comments

[jodag]

just a word of warning about bicubic interpolation is that the range of the result may be wider than the range of the input. If this is important than you can use bilinear instead