地瓜官网
地瓜开发者社区
地瓜官网
地瓜开发者社区

nn.functional.point_pillars_preprocess

horizon_plugin_pytorch.nn.functional.point_pillars_preprocess (points_list: List[Tensor], pc_range: Tensor, voxel_size: Tensor, max_voxels: int, max_points_per_voxel: int, use_max: bool, norm_range: Tensor, norm_dims: Tensor)

Preprocess PointPillars.

Parameters:

points_list (List[Tensor]) – [(M1, ndim), (M2, ndim),…], List of PointCloud data.

pc_range (Tensor) – (6,), indicate voxel range, format: [x_min, y_min, z_min, x_max, y_max, z_max]

voxel_size (Tensor) – (3,), xyz, indicate voxel size.

max_voxels (int) – Indicate maximum voxels.

max_points_per_voxel (int) – Indicate maximum points contained in a voxel.

use_max (bool) – Whether to use max_voxels, for deploy should be True.

norm_range (Tensor) – Feature range, like [x_min, y_min, z_min, …, x_max, y_max, z_max, …].

norm_dims (Tensor) – Dims to do normalize.

Returns: (features, coords), encoded feature and coordinates in (idx, z, y, x) format.

Return type: (Tensor, Tensor)