Skip to content

Conversation

NicolasHug
Copy link
Member

part of #3865

[10, 15, 30, 35], [23, 35, 93, 95]], dtype=torch.float)

box_same = ops.box_convert(box_tensor, in_fmt="xyxy", out_fmt="xyxy")
self.assertEqual(exp_xyxy.size(), torch.Size([4, 4]))
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think that we shoudn't remove self.assertEqual(exp_xyxy.size(), torch.Size([4, 4])) as it's not the same as comparing exp_xyxy.size() vs box_tensor.size(), so I'll put these back

Copy link
Member Author

@NicolasHug NicolasHug left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM!

Copy link
Contributor

@datumbox datumbox left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Stamping

@NicolasHug NicolasHug merged commit 55150bf into pytorch:master May 21, 2021
facebook-github-bot pushed a commit that referenced this pull request May 25, 2021
Summary: Co-authored-by: Philip Meier <github.pmeier@posteo.de>

Reviewed By: vincentqb, cpuhrsch

Differential Revision: D28679978

fbshipit-source-id: 1699926c8d738e904603e40f87b6b3087d3d37bd
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants