detectionmetrics.models.torch_model_utils package

Submodules

detectionmetrics.models.torch_model_utils.o3d_randlanet module

detectionmetrics.models.torch_model_utils.o3d_randlanet.transform_input(points: ndarray, cfg: dict, sampler: Sampler | None = None) → Tuple[Tuple[torch.Tensor, List[torch.Tensor], List[torch.Tensor], List[torch.Tensor], List[torch.Tensor]], ndarray]

Transform point cloud data into input data for the model

Parameters:

• points (np.ndarray) – Point cloud data

• cfg (dict) – Dictionary containing model configuration file

• sampler (Optional[ul.Sampler], optional) – Object for sampling point cloud, defaults to None

Returns:

Model input data and selected indices

Return type:

Tuple[ Tuple[ torch.Tensor, List[torch.Tensor], List[torch.Tensor], List[torch.Tensor], List[torch.Tensor], ], np.ndarray, ]

detectionmetrics.models.torch_model_utils.o3d_randlanet.update_probs(new_probs: torch.Tensor, indices: torch.Tensor, test_probs: torch.Tensor, n_classes: int, weight: float = 0.95) → torch.Tensor

Update test probabilities with new model output using weighted average for a smooth transition between predictions

Parameters:

• new_probs (torch.Tensor) – New probabilities to be added to the test probabilities

• indices (torch.Tensor) – Corresponding indices of the new probabilities

• test_probs (torch.Tensor) – Test probabilities to be updated

• n_classes (int) – Number of classes

• weight (float, optional) – Weight used in the weighted average, defaults to 0.95

Returns:

Updated test probabilities

Return type:

torch.Tensor

Module contents

detectionmetrics.models.torch_model_utils.preprocess(points: ndarray, cfg: dict | None = {}) → Tuple[ndarray, KDTree, ndarray]

Preprocess point cloud data

Parameters:

• points (np.ndarray) – Point cloud data

• cfg (Optional[dict], optional) – Dictionary containing model configuration, defaults to {}

Returns:

Subsampled points, search tree, and projected indices

Return type:

Tuple[np.ndarray, KDTree, np.ndarray]