Skip to content
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

Adds torchscript Compatibility to box_convert #2737

Merged
merged 10 commits into from
Oct 7, 2020
Merged

Adds torchscript Compatibility to box_convert #2737

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
1dd9189
fixies small bug in box_convert
oke-aditya Oct 1, 2020
6cbdf27
activates jit test
oke-aditya Oct 1, 2020
ff8b906
Merge branch 'master' into tscript_bbox
oke-aditya Oct 5, 2020
08a3567
Passes JIT test
oke-aditya Oct 5, 2020
605306c
Merge branch 'tscript_bbox' of github.com:oke-aditya/vision into tscr…
oke-aditya Oct 5, 2020
11ab169
Merge branch 'master' into tscript_bbox
oke-aditya Oct 5, 2020
169d1bc
fixes typo
oke-aditya Oct 5, 2020
fd5c660
adds error tests, removes assert
oke-aditya Oct 5, 2020
f8114c6
implements to proposal2
oke-aditya Oct 7, 2020
3094f03
Merge branch 'master' into tscript_bbox
oke-aditya Oct 7, 2020
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
22 changes: 11 additions & 11 deletions test/test_ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -727,20 +727,20 @@ def test_bbox_xywh_cxcywh(self):
self.assertEqual(box_xywh.dtype, box_tensor.dtype)
assert torch.all(torch.eq(box_xywh, box_tensor)).item()

# def test_bbox_convert_jit(self):
# box_tensor = torch.tensor([[0, 0, 100, 100], [0, 0, 0, 0],
# [10, 15, 30, 35], [23, 35, 93, 95]], dtype=torch.float)
def test_bbox_convert_jit(self):
Copy link
Collaborator

Choose a reason for hiding this comment

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

I was wondering if it would be more simple to check scripted function in all your test_bbox_*:

scripted_fn = torch.jit.script(ops.box_convert)

for fn in [ops.box_convert, scripted_fn]:
    # ...

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Possible, this PR is open for a lot of refactoring 👍 .

box_tensor = torch.tensor([[0, 0, 100, 100], [0, 0, 0, 0],
[10, 15, 30, 35], [23, 35, 93, 95]], dtype=torch.float)

# scripted_fn = torch.jit.script(ops.box_convert)
# TOLERANCE = 1e-3
scripted_fn = torch.jit.script(ops.box_convert)
TOLERANCE = 1e-3

# box_xywh = ops.box_convert(box_tensor, in_fmt="xyxy", out_fmt="xywh")
# scripted_xywh = scripted_fn(box_tensor, 'xyxy', 'xywh')
# self.assertTrue((scripted_xywh - box_xywh).abs().max() < TOLERANCE)
box_xywh = ops.box_convert(box_tensor, in_fmt="xyxy", out_fmt="xywh")
scripted_xywh = scripted_fn(box_tensor, 'xyxy', 'xywh')
self.assertTrue((scripted_xywh - box_xywh).abs().max() < TOLERANCE)

# box_cxcywh = ops.box_convert(box_tensor, in_fmt="xyxy", out_fmt="cxcywh")
# scripted_cxcywh = scripted_fn(box_tensor, 'xyxy', 'cxcywh')
# self.assertTrue((scripted_cxcywh - box_cxcywh).abs().max() < TOLERANCE)
box_cxcywh = ops.box_convert(box_tensor, in_fmt="xyxy", out_fmt="cxcywh")
scripted_cxcywh = scripted_fn(box_tensor, 'xyxy', 'cxcywh')
self.assertTrue((scripted_cxcywh - box_cxcywh).abs().max() < TOLERANCE)


class BoxAreaTester(unittest.TestCase):
Expand Down
6 changes: 3 additions & 3 deletions torchvision/ops/_box_convert.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,7 +77,7 @@ def _box_xyxy_to_xywh(boxes: Tensor) -> Tensor:
boxes (Tensor[N, 4]): boxes in (x, y, w, h) format.
"""
x1, y1, x2, y2 = boxes.unbind(-1)
x2 = x2 - x1 # x2 - x1
y2 = y2 - y1 # y2 - y1
boxes = torch.stack((x1, y1, x2, y2), dim=-1)
w = x2 - x1 # x2 - x1
h = y2 - y1 # y2 - y1
boxes = torch.stack((x1, y1, w, h), dim=-1)
return boxes