Update unittest for mmdet3d ops (#1811)

tests/test_ops/test_gather_points.py

@@ -45,3 +45,7 @@ def test_gather_points():
           [-0.7172, 0.0462, -0.6227, -0.7172, -0.7172, -0.7172]]]).cuda()
 
     assert torch.allclose(output, expected_output)
+
+    # test fp16
+    output_half = gather_points(features.half(), idx)
+    assert torch.allclose(output_half, expected_output.half())

tests/test_ops/test_roiaware_pool3d.py

@@ -133,3 +133,11 @@ def test_points_in_boxes_all():
         dtype=torch.int32).cuda()
     assert point_indices.shape == torch.Size([1, 15, 2])
     assert (point_indices == expected_point_indices).all()
+
+    if torch.cuda.device_count() > 1:
+        pts = pts.to('cuda:1')
+        boxes = boxes.to('cuda:1')
+        expected_point_indices = expected_point_indices.to('cuda:1')
+        point_indices = points_in_boxes_all(points=pts, boxes=boxes)
+        assert point_indices.shape == torch.Size([1, 15, 2])
+        assert (point_indices == expected_point_indices).all()

tests/test_ops/test_roipoint_pool3d.py

@@ -7,7 +7,7 @@ from mmcv.ops import RoIPointPool3d
 
 @pytest.mark.skipif(
     not torch.cuda.is_available(), reason='requires CUDA support')
-def test_gather_points():
+def test_roipoint():
     feats = torch.tensor(
         [[1, 2, 3.3], [1.2, 2.5, 3.0], [0.8, 2.1, 3.5], [1.6, 2.6, 3.6],
          [0.8, 1.2, 3.9], [-9.2, 21.0, 18.2], [3.8, 7.9, 6.3],

tests/test_ops/test_scatter_points.py

@@ -9,11 +9,6 @@ from mmcv.ops import DynamicScatter
 @pytest.mark.skipif(
     not torch.cuda.is_available(), reason='requires CUDA support')
 def test_dynamic_scatter():
-    feats = torch.rand(
-        size=(200000, 3), dtype=torch.float32, device='cuda') * 100 - 50
-    coors = torch.randint(
-        low=-1, high=20, size=(200000, 3), dtype=torch.int32, device='cuda')
-
     dsmean = DynamicScatter([0.32, 0.32, 6],
                             [-74.88, -74.88, -2, 74.88, 74.88, 4], True)
     dsmax = DynamicScatter([0.32, 0.32, 6],
@@ -53,6 +48,11 @@ def test_dynamic_scatter():
     assert (empty_o_feats.grad == 0).all()
 
     # test non-empty input
+    feats = torch.rand(
+        size=(200000, 3), dtype=torch.float32, device='cuda') * 100 - 50
+    coors = torch.randint(
+        low=-1, high=20, size=(200000, 3), dtype=torch.int32, device='cuda')
+
     ref_voxel_coors = coors.unique(dim=0, sorted=True)
     ref_voxel_coors = ref_voxel_coors[ref_voxel_coors.min(dim=-1).values >= 0]
     ref_voxel_feats_mean = []