Consider the following 6x6 tensor. tst_tensor = tensor([[1, 1, 1, 2, 3, 1], [1, 2, 0, 0, 0, 0], [1, 0, 1, 0, 0, 0], [5, 5, 5, 5, 5, 5], [5, 5, 5, 0, 0, 0], [0, 2, 3, 0, 0, 0]]) I’d like to window it in 2x2 windows (or 4 x 1) as follows tensor([[1, 1, 1, 2],…

For getting tiles, manually doing this is probably most efficient: windows = tst_tensor.view(3, 2, 3, 2).permute(0, 2, 1, 3).reshape(1, 9, 4) Best regards Thomas

I’m not sure, how the example result would fit into a [4, 1] window, but you could try to use tensor.unfold, which will not collapse the patches into a dimension: tst_tensor = torch.tensor([[1, 1, 1, 2, 3, 1], [1, 2, 0, 0, 0, 0], [1, 0, 1, 0, 0, 0], …

That’s definitely a lot closer than I’ve gotten! To give some background, the reason I’m trying to do this is to “shrink” a larger matrix by cutting it up into windows and then taking the mode of these windows. Similar to how you would interpolate an image, but by taking the mode instead of some mea…

@tom Thank you for your reply! If anyone else finds it useful, below is a function that implements what Thomas suggested in a more general way. It behaves the same way the original did (compared using a dataset of 480 x 640 images) AFAIK. def fastCreateFeatureMap(masks, num_x_windows = 48, num_y_w…

PyTorch Forums

Proper use of unfold?

ptrblck February 25, 2020, 4:27pm 4

Have a look at this code.

show post in topic

Home
Categories
Guidelines
Terms of Service
Privacy Policy

Powered by Discourse, best viewed with JavaScript enabled