New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

MaskToRegion is 1 pixel too large #6

Open

Acly opened this issue Aug 22, 2023 · 1 comment

Acly commented Aug 22, 2023

Reproducer:

>>> mask = torch.zeros([1, 4, 4])
>>> mask[0, 0:2, 0:2] = torch.ones([2, 2])
>>> mask
tensor([[[1., 1., 0., 0.],
         [1., 1., 0., 0.],
         [0., 0., 0., 0.],
         [0., 0., 0., 0.]]])
>>> MaskNodes.MaskToRegion().get_region(mask, 0, 'multiple_of', 2, 2, 0, 0, 'match_ratio')
(tensor([[[1., 1., 1., 0.],
         [1., 1., 1., 0.],
         [1., 1., 1., 0.],
         [0., 0., 0., 0.]]]),)

I believe the width/height calculation is wrong? it should rather be:

width = max_x - min_x + 1
height = max_y - min_y + 1

The text was updated successfully, but these errors were encountered:

Author

Acly commented Aug 22, 2023

Also this code should probably clamp max_x/max_y to the mask's max, ie. mask_width - 1 and mask_height - 1.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment