open3d.ml.torch.datasets.NuScenes#

class open3d.ml.torch.datasets.NuScenes(dataset_path, info_path=None, name='NuScenes', cache_dir='./logs/cache', use_cache=False, **kwargs)#

This class is used to create a dataset based on the NuScenes 3D dataset, and used in object detection, visualizer, training, or testing.

The NuScenes 3D dataset is best suited for autonomous driving applications.

__init__(dataset_path, info_path=None, name='NuScenes', cache_dir='./logs/cache', use_cache=False, **kwargs)#

Initialize the function by passing the dataset and other details.

Parameters:

  • dataset_path – The path to the dataset to use.

  • info_path – The path to the file that includes information about the dataset. This is default to dataset path if nothing is provided.

  • name – The name of the dataset (NuScenes in this case).

  • cache_dir – The directory where the cache is stored.

  • use_cache – Indicates if the dataset should be cached.

Returns:

The corresponding class.

Return type:

class

static get_label_to_names()#

Returns a label to names dictionary object.

Returns:

A dict where keys are label numbers and values are the corresponding names.

get_split(split)#

Returns a dataset split.

Parameters:

  • split – A string identifying the dataset split that is usually one of

  • 'training' –

  • 'test' –

  • 'validation' –

  • 'all'. (or) –

Returns:

A dataset split object providing the requested subset of the data.

get_split_list(split)#

Returns the list of data splits available.

Parameters:

  • split – A string identifying the dataset split that is usually one of

  • 'training' –

  • 'test' –

  • 'validation' –

  • 'all'. (or) –

Returns:

A dataset split object providing the requested subset of the data.

Raises:

ValueError – Indicates that the split name passed is incorrect. The split name should be one of ‘training’, ‘test’, ‘validation’, or ‘all’.

is_tested()#

Checks if a datum in the dataset has been tested.

Parameters:

dataset – The current dataset to which the datum belongs to. attr: The attribute that needs to be checked.

Returns:

If the dataum attribute is tested, then return the path where the

attribute is stored; else, returns false.

read_cams(cam_dict)#

Reads image data from the cam dict provided.

Parameters:

cam_dict (Dict) – Mapping from camera names to dict with image information (‘data_path’, ‘sensor2lidar_translation’, ‘sensor2lidar_rotation’, ‘cam_intrinsic’).

Returns:

A dict with keys as camera names and value as images.

static read_label(info, calib)#

Reads labels of bound boxes.

Returns:

The data objects with bound boxes information.

static read_lidar(path)#

Reads lidar data from the path provided.

Returns:

A data object with lidar information.

save_test_result()#

Saves the output of a model.

Parameters:

  • results – The output of a model for the datum associated with the attribute passed.

  • attr – The attributes that correspond to the outputs passed in results.