423A35C7/pytorch3d
1
0
Fork 0
mirror of https://github.com/facebookresearch/pytorch3d.git synced 2025-12-19 22:00:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

chamfer for empty pointclouds #1174

Browse Source 
Summary: Fix divide by zero for empty pointcloud in chamfer. Also for empty batches. In process, needed to regularize num_points_per_cloud for empty batches.

Reviewed By: kjchalup

Differential Revision: D36311330

fbshipit-source-id: 3378ab738bee77ecc286f2110a5c8dc445960340
This commit is contained in:
Jeremy Reizenstein
2022-05-26 14:56:22 -07:00
committed by Facebook GitHub Bot
parent a42a89a5ba
commit c6519f29f0
5 changed files with 24 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
tests/test_chamfer.py
View File

@@ -778,6 +778,17 @@ class TestChamfer(TestCaseMixin, unittest.TestCase):
with self.assertRaisesRegex(ValueError, "Support for 1 or 2 norm."):
chamfer_distance(p1, p2, norm=3)
def test_empty_clouds(self):
# Check that point_reduction doesn't divide by zero
points1 = Pointclouds(points=[torch.zeros(0, 3), torch.zeros(10, 3)])
points2 = Pointclouds(points=torch.ones(2, 40, 3))
loss, _ = chamfer_distance(points1, points2, batch_reduction=None)
self.assertClose(loss, torch.tensor([0.0, 6.0]))
# Check that batch_reduction doesn't divide by zero
loss2, _ = chamfer_distance(Pointclouds([]), Pointclouds([]))
self.assertClose(loss2, torch.tensor(0.0))
@staticmethod
def chamfer_with_init(
batch_size: int,