Skip to content

Clip horizontal bounding boxes during rotated detection for backward compatibility#9403

Closed
vishar0 wants to merge 1 commit intopytorch:masterfrom
vishar0:export-D8828588
Closed

Clip horizontal bounding boxes during rotated detection for backward compatibility#9403
vishar0 wants to merge 1 commit intopytorch:masterfrom
vishar0:export-D8828588

Conversation

@vishar0
Copy link
Contributor

@vishar0 vishar0 commented Jul 12, 2018

Summary:
In BBoxTransform and GenerateProposal ops, clip_boxes makes sure the bbox fits
within the images. For rotated boxes, this doesn't always make sense as there
could be multiple ways to clip a rotated box within an image boundary.
Moreover, clipping to a horizontal box means we leave out pixels of interest
potentially. Therefore, we clip only boxes with angle almost equal to 0 (with a
specified angle_thresh tolerance).

Differential Revision: D8828588

…compatibility (pytorch#9403)

Summary:
Pull Request resolved: pytorch#9403

In BBoxTransform and GenerateProposal ops, clip_boxes makes sure the bbox fits
within the images. For rotated boxes, this doesn't always make sense as there
could be multiple ways to clip a rotated box within an image boundary.
Moreover, clipping to a horizontal box means we leave out pixels of interest
potentially. Therefore, we clip only boxes with angle almost equal to 0 (with a
specified `angle_thresh` tolerance).

Differential Revision: D8828588

fbshipit-source-id: b671f2314e7a1252e2e8669cdc06f83c74696eea
goldsborough pushed a commit to goldsborough/pytorch that referenced this pull request Jul 20, 2018
…compatibility (pytorch#9403)

Summary:
Pull Request resolved: pytorch#9403

In BBoxTransform and GenerateProposal ops, clip_boxes makes sure the bbox fits
within the images. For rotated boxes, this doesn't always make sense as there
could be multiple ways to clip a rotated box within an image boundary.
Moreover, clipping to a horizontal box means we leave out pixels of interest
potentially. Therefore, we clip only boxes with angle almost equal to 0 (with a
specified `angle_thresh` tolerance).

Reviewed By: pjh5

Differential Revision: D8828588

fbshipit-source-id: 39c1eafdb5d39d383780faa0a47e76149145e50c
jramseyer pushed a commit to jramseyer/pytorch that referenced this pull request Jul 30, 2018
…compatibility (pytorch#9403)

Summary:
Pull Request resolved: pytorch#9403

In BBoxTransform and GenerateProposal ops, clip_boxes makes sure the bbox fits
within the images. For rotated boxes, this doesn't always make sense as there
could be multiple ways to clip a rotated box within an image boundary.
Moreover, clipping to a horizontal box means we leave out pixels of interest
potentially. Therefore, we clip only boxes with angle almost equal to 0 (with a
specified `angle_thresh` tolerance).

Reviewed By: pjh5

Differential Revision: D8828588

fbshipit-source-id: 39c1eafdb5d39d383780faa0a47e76149145e50c
goodlux pushed a commit to goodlux/pytorch that referenced this pull request Aug 15, 2018
…compatibility (pytorch#9403)

Summary:
Pull Request resolved: pytorch#9403

In BBoxTransform and GenerateProposal ops, clip_boxes makes sure the bbox fits
within the images. For rotated boxes, this doesn't always make sense as there
could be multiple ways to clip a rotated box within an image boundary.
Moreover, clipping to a horizontal box means we leave out pixels of interest
potentially. Therefore, we clip only boxes with angle almost equal to 0 (with a
specified `angle_thresh` tolerance).

Reviewed By: pjh5

Differential Revision: D8828588

fbshipit-source-id: 39c1eafdb5d39d383780faa0a47e76149145e50c
@ezyang ezyang added the merged label Jun 26, 2019
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants