Skip to content

[Update] test bbox nms #115

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

Merged
merged 2 commits into from
Nov 7, 2024
Merged

[Update] test bbox nms #115

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4a89507
Update comment about the expected output from bbox_nms
f-fl0 Nov 5, 2024
68ef704
Remove debug print
f-fl0 Nov 5, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 8 additions & 7 deletions tests/test_utils/test_bounding_box_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -185,13 +185,15 @@ def test_bbox_nms():
nms_cfg = NMSConfig(min_confidence=0.5, min_iou=0.5, max_bbox=400)

# Batch 1:
# - box 1 is kept with class 0 as it has a higher confidence than box 4 i.e. box 4 is filtered out
# - box 2 is kept with class 1
# - box 3 is rejected by the confidence filter
# - box 1 is kept with classes 0 and 2 as it overlaps with box 4 and has a higher confidence for classes 0 and 2.
# - box 2 is kept with classes 0, 1, 2 as it does not overlap with any other box.
# - box 3 is rejected by the confidence filter.
# - box 4 is kept with class 1 as it overlaps with box 1 and has a higher confidence for class 1.
# Batch 2:
# - box 4 is kept with class 0 as it has a higher confidence than box 1 i.e. box 1 is filtered out
# - box 2 is rejected by the confidence filter
# - box 3 is kept with class 2
# - box 1 is kept with classes 1 and 2 as it overlaps with box 1 and has a higher confidence for classes 1 and 2.
# - box 2 is rejected by the confidence filter.
# - box 3 is kept with classes 0, 1, 2 as it does not overlap with any other box.
# - box 4 is kept with class 0 as it overlaps with box 1 and has a higher confidence for class 0.
expected_output = torch.tensor(
[
[
Expand All @@ -214,7 +216,6 @@ def test_bbox_nms():
)

output = bbox_nms(cls_dist, bbox, nms_cfg)
print(output)
for out, exp in zip(output, expected_output):
assert allclose(out, exp, atol=1e-4), f"Output: {out} Expected: {exp}"

Expand Down
Loading