waxmorph.torch.losses.squared_loss

waxmorph.torch.losses.squared_loss(X_pred, X_target)

Squared Frobenius loss for row-aligned clouds.

\[\mathcal{L} = \lVert X^f - X^T \rVert_F^2\]

Rows are fixed correspondences and shapes must match. Use chamfer_distance() or make_samples_loss() for unordered rows.

Examples

>>> x = torch.tensor([[0.0, 0.0, 0.0], [1.0, 0.0, 0.0]])
>>> y = torch.tensor([[0.0, 0.0, 0.0], [2.0, 0.0, 0.0]])
>>> print(squared_loss(x, y))
tensor(1.)

Parameters:

• X_pred (Tensor)

• X_target (Tensor)

Return type:

Tensor