open3d.ml.tf.datasets.Scannet

class open3d.ml.tf.datasets.Scannet(dataset_path, name='Scannet', cache_dir='./logs/cache', use_cache=False, **kwargs)

Scannet 3D dataset for Object Detection, used in visualizer, training, or test.

__init__(dataset_path, name='Scannet', cache_dir='./logs/cache', use_cache=False, **kwargs)

Initialize the dataset by passing the dataset and other details.

Parameters

• dataset_path (str) – The path to the dataset to use.

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

• cache_dir (str) – The directory where the cache is stored.

• use_cache (bool) – Indicates if the dataset should be cached.

get_label_to_names()

Returns a label to names dictonary 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)

is_tested()

Checks whether a datum has been tested.

Parameters

attr – The attributes associated with the datum.

Returns

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

read_label(scene)

static read_lidar(path)

save_test_result(results, attr)

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.