Object3D

Class wandb.Object3D

W&B class for 3D point clouds.

data_or_path: 'np.ndarray | str | pathlib.Path | TextIO | dict',
caption: 'str | None' = None, **kwargs: 'str | FileFormat3D | None'

Args

np.ndarray | str | pathlib.Path | TextIO | dict

Object3D can be initialized from a file or a numpy array.

str | None

Caption associated with the object for display.

str | FileFormat3D | None

No description provided.

Methods

method Object3D.from_file()

data_or_path: 'TextIO | str',
file_type: 'FileFormat3D | None' = None

Initializes Object3D from a file or stream.

Arguments

TextIO | str

A path to a file or a TextIO stream.

method Object3D.from_numpy()

data: 'np.ndarray'

Initializes Object3D from a numpy array.

method Object3D.from_point_cloud()

points: 'Sequence[Point]',
boxes: 'Sequence[Box3D]',
vectors: 'Sequence[Vector3D] | None' = None,
point_cloud_type: 'PointCloudType' = 'lidar/beta'

Initializes Object3D from a python object.

Arguments

Sequence[Point]

The points in the point cloud.

Sequence[Box3D]

3D bounding boxes for labeling the point cloud. Boxes are displayed in point cloud visualizations.

Sequence[Vector3D] | None

Each vector is displayed in the point cloud visualization. Can be used to indicate directionality of bounding boxes. Defaults to None.

W&B Models

W&B Weave

Serverless Inference

Serverless Training

Class wandb.Object3D

Args

Methods

method Object3D.from_file()

Arguments

method Object3D.from_numpy()

method Object3D.from_point_cloud()

Arguments

​Class wandb.Object3D

​Args

​Methods

​method Object3D.from_file()

Arguments

​method Object3D.from_numpy()

​method Object3D.from_point_cloud()

Arguments

Class wandb.Object3D

Args

Methods

method Object3D.from_file()

method Object3D.from_numpy()

method Object3D.from_point_cloud()