open3d.ml.torch.datasets.Semantic3D

class open3d.ml.torch.datasets.Semantic3D(dataset_path, name='Semantic3D', cache_dir='./logs/cache', use_cache=False, num_points=65536, class_weights=[5181602, 5012952, 6830086, 1311528, 10476365, 946982, 334860, 269353], ignored_label_inds=[0], val_files=['bildstein_station3_xyz_intensity_rgb', 'sg27_station2_intensity_rgb'], test_result_folder='./test', **kwargs)

SemanticKITTI dataset, used in visualizer, training, or test

__init__(dataset_path, name='Semantic3D', cache_dir='./logs/cache', use_cache=False, num_points=65536, class_weights=[5181602, 5012952, 6830086, 1311528, 10476365, 946982, 334860, 269353], ignored_label_inds=[0], val_files=['bildstein_station3_xyz_intensity_rgb', 'sg27_station2_intensity_rgb'], test_result_folder='./test', **kwargs)

Initialize :param dataset_path: path to the dataset :param kwargs:

Returns

The corresponding class.

Return type

class

static get_label_to_names()

Returns a label to names dict.

Returns

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

get_split(split)

Returns a dataset split.

Parameters

• split – A string identifying the dataset split. Usually one of

• 'test', 'validation', 'all'. ('training',) –

Returns

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

get_split_list(split)

is_tested(attr)

Checks whether a datum has been tested.

Parameters

attr – The attributes associated with the datum

Returns

True if the test result has been stored for the datum with the specified attribute or else returns False.

save_test_result(results, attr)

Saves the output of a model.

Parameters

• results – The output of a model for the datum associated with ‘attr’.

• attr – The attributes that correspond to the outputs ‘results’.