Add rotated bounding box formats #8841
Open
+549
−28
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Test Plan: Run unit tests: `pytest test/test_ops.py -vvv -k TestBoxConvert`
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/vision/8841
Note: Links to docs will display an error until the docs builds have been completed. ❌ 15 New Failures, 1 Unrelated FailureAs of commit 3f437a6 with merge base 4249b61 ( NEW FAILURES - The following jobs have failed:
BROKEN TRUNK - The following job failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
NicolasHug
reviewed
Jan 13, 2025
There was a problem hiding this comment.
Thanks a lot for the PR @AntoineSimoulin ! I made some small comments below, I have higher-level points to discuss, let's sync! :)
| """:class:`torch.Tensor` subclass for bounding boxes with shape ``[N, 4]``. | ||
| """:class:`torch.Tensor` subclass for bounding boxes with shape ``[N, K]``. | ||
| Where ``N`` is the number of bounding boxes | ||
| and ``K`` is either 4 for unrotated boxes or 5 for rotated boxes. |
There was a problem hiding this comment.
Suggested change
| and ``K`` is either 4 for unrotated boxes or 5 for rotated boxes. | |
| and ``K`` is 4 for unrotated boxes, and 5 or 8 for rotated boxes. |
| @@ -17,15 +17,25 @@ class BoundingBoxFormat(Enum): | |||
| * ``XYXY`` | |||
| * ``XYWH`` | |||
| * ``CXCYWH`` | |||
| * ``XYXYR``: rotated boxes represented via corners, x1, y1 being top left and x2, y2 being bottom right. r is rotation angle in degrees. | |||
There was a problem hiding this comment.
Just to make it more explicit
Suggested change
| * ``XYXYR``: rotated boxes represented via corners, x1, y1 being top left and x2, y2 being bottom right. r is rotation angle in degrees. | |
| * ``XYXYR``: rotated boxes represented via corners, x1, y1 being top left and x2, y2 being bottom right. r is rotation angle in degrees in [0, 360). |
| @@ -1288,6 +1288,38 @@ def test_bbox_same(self): | |||
| assert_equal(ops.box_convert(box_tensor, in_fmt="xywh", out_fmt="xywh"), exp_xyxy) | |||
| assert_equal(ops.box_convert(box_tensor, in_fmt="cxcywh", out_fmt="cxcywh"), exp_xyxy) | |||
|
|
|||
| def test_rotated_bbox_same(self): | |||
There was a problem hiding this comment.
I think this kind of check is already taken care of in
vision/test/test_transforms_v2.py
Lines 3521 to 3531 in 06a925c
|
|
||
| assert exp_xywhr.size() == torch.Size([6, 5]) | ||
| box_xywhr = ops.box_convert(box_tensor, in_fmt="xyxyr", out_fmt="xywhr") | ||
| assert torch.allclose(box_xywhr, exp_xywhr) |
There was a problem hiding this comment.
Let's use torch.testing.assert_close() instead of torch.allclose, as it's more robust and provides better messages.
That being said, could we use assert_equal() here, since we're expecting integer-valued tensors? Is it because of the r column?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR is part of a series of contributions aiming to add rotated boxes to torchvision. This first contribution aims at modifying the definition of bounding boxes in torchvision. We operate the two following modifications:
Extend
BoundingBoxFormatfor rotated boxesWe add four multiple allowed formats in
BoundingBoxFormat. The formats "xyxyr", "xywhr", "cxcywhr" simply extend the non-rotated counterparts by adding a 5th coordinate to the bounding box,r, the rotation angle with respect to the box center by|r|degrees counter clock wise in the image plan. The last format "xyxyxyxy" represents a box with 4 corners.Potential limitations:
BoundingBoxesinstead of creating a newRoratedBoundingBoxesclass. The reason is to simplify the possible input types for transforms and avoid having two different paths for transformations. For instance keeping a singlehorizontal_flip_bounding_boxesand_horizontal_flip_bounding_boxes_dispatchinstead of creating a new functionhorizontal_flip_rotated_bounding_boxes;generalized_box_iou_loss. However, please note these functions do not expect aBoundingBoxas input, but atorch.Tensor[N, 4]ortorch.Tensor[4]. So there is no direct incompatibility.Add conversion functions for rotated boxes
We add 10 pairwise conversion functions in "_box_convert.py" to allow converting rotated bounding boxes between all four new formats. We also modified the logic in
box_convertto support all possible conversion directions.Potential limitations:
Testing
Please run unit tests for the modifications with:
pytest test/test_ops.py -vvv -k TestBoxConvertNext steps
Next modifications will aim at updating transforms functions (e.g.
horizontal_flip_bounding_boxes), and adding utility functions specific to rotated boxes (e.g.rotated_box_area,_rotated_box_inter_union,rotated_box_iou).