def furthest_point_sample(xyz, npoint):
# type: (Any, torch.Tensor, int) -> torch.Tensor
r"""
Uses iterative furthest point sampling to select a set of npoint features that have the largest
minimum distance
Parameters
----------
xyz : torch.Tensor
(B, N, 3) tensor where N > npoint
npoint : int32
number of features in the sampled set
Returns
-------
torch.Tensor
(B, npoint) tensor containing the set
"""
if npoint > xyz.shape[1]:
raise ValueError(
"caanot sample %i points from an input set of %i points" %
(npoint, xyz.shape[1]))
if xyz.is_cuda:
return tpcuda.furthest_point_sampling(xyz, npoint)
else:
return tpcpu.fps(xyz, npoint, True)
def test_random(self):
points = torch.randn(10, 100, 3)
idx = fps(points, 2, True)
self.assertNotEqual(idx[0][0], 0)
def test_simplecpu(self):
points = torch.tensor([[[0, 0, 0], [1, 0, 0], [2, 0, 0]],
[[-1, 1, 0], [0, 0, 10], [0, 0, 2]]]).float()
idx = fps(points, 2, False)
torch.testing.assert_allclose(idx, torch.tensor([[0, 2], [0, 1]]))