kaolin.metrics.voxelgrid¶
API¶
- kaolin.metrics.voxelgrid.iou(pred, gt)¶
Computes IoU across two voxelgrids
- Parameters
pred (torch.Tensor) – predicted (binary) voxelgrids, of shape \((\text{batch_size}, \text{X}, \text{Y}, \text{Z})\).
gt (torch.Tensor) – ground-truth (binary) voxelgrids, of shape \((\text{batch_size}, \text{X}, \text{Y}, \text{Z})\).
- Returns
the intersection over union value.
- Return type
(torch.FloatTensor)
Example
>>> pred = torch.tensor([[[[0., 0.], ... [1., 1.]], ... [[1., 1.], ... [1., 1.]]]]) >>> gt = torch.ones((1,2,2,2)) >>> iou(pred, gt) tensor([0.7500])