nearest.py

import torch
import scipy.cluster

if torch.cuda.is_available():
    import torch_cluster.nearest_cuda


def nearest(x, y, batch_x=None, batch_y=None):
    r"""Clusters points in :obj:`x` together which are nearest to a given query
    point in :obj:`y`.

    Args:
        x (Tensor): Node feature matrix
            :math:`\mathbf{X} \in \mathbb{R}^{N \times F}`.
        y (Tensor): Node feature matrix
            :math:`\mathbf{X} \in \mathbb{R}^{M \times F}`.
        batch_x (LongTensor, optional): Batch vector
            :math:`\mathbf{b} \in {\{ 0, \ldots, B-1\}}^N`, which assigns each
            node to a specific example. (default: :obj:`None`)
        batch_y (LongTensor, optional): Batch vector
            :math:`\mathbf{b} \in {\{ 0, \ldots, B-1\}}^M`, which assigns each
            node to a specific example. (default: :obj:`None`)

    .. testsetup::

        import torch
        from torch_cluster import nearest

    .. testcode::

        >>> x = torch.Tensor([[-1, -1], [-1, 1], [1, -1], [1, 1]])
        >>> batch_x = torch.tensor([0, 0, 0, 0])
        >>> y = torch.Tensor([[-1, 0], [1, 0]])
        >>> batch_x = torch.tensor([0, 0])
        >>> cluster = nearest(x, y, batch_x, batch_y)
    """

    if batch_x is None:
        batch_x = x.new_zeros(x.size(0), dtype=torch.long)

    if batch_y is None:
        batch_y = y.new_zeros(y.size(0), dtype=torch.long)

    x = x.view(-1, 1) if x.dim() == 1 else x
    y = y.view(-1, 1) if y.dim() == 1 else y

    assert x.dim() == 2 and batch_x.dim() == 1
    assert y.dim() == 2 and batch_y.dim() == 1
    assert x.size(1) == y.size(1)
    assert x.size(0) == batch_x.size(0)
    assert y.size(0) == batch_y.size(0)

    if x.is_cuda:
        return torch_cluster.nearest_cuda.nearest(x, y, batch_x, batch_y)

    # Rescale x and y.
    min_xy = min(x.min().item(), y.min().item())
    x, y = x - min_xy, y - min_xy

    max_xy = max(x.max().item(), y.max().item())
    x, y, = x / max_xy, y / max_xy

    # Concat batch/features to ensure no cross-links between examples exist.
    x = torch.cat([x, 2 * x.size(1) * batch_x.view(-1, 1).to(x.dtype)], dim=-1)
    y = torch.cat([y, 2 * y.size(1) * batch_y.view(-1, 1).to(y.dtype)], dim=-1)

    return torch.from_numpy(scipy.cluster.vq.vq(x, y)[0]).to(torch.long)