cloudViewer.ml.torch.datasets.S3DIS#

class cloudViewer.ml.torch.datasets.S3DIS(dataset_path, name='S3DIS', task='segmentation', cache_dir='./logs/cache', use_cache=False, class_weights=[3370714, 2856755, 4919229, 318158, 375640, 478001, 974733, 650464, 791496, 88727, 1284130, 229758, 2272837], num_points=40960, test_area_idx=3, ignored_label_inds=[], ignored_objects=['wall', 'floor', 'ceiling', 'beam', 'column', 'clutter'], test_result_folder='./test', **kwargs)[source]#

This class is used to create a dataset based on the S3DIS (Stanford Large-Scale 3D Indoor Spaces) dataset, and used in visualizer, training, or testing.

The S3DIS dataset is best used to train models for building indoors.

__init__(dataset_path, name='S3DIS', task='segmentation', cache_dir='./logs/cache', use_cache=False, class_weights=[3370714, 2856755, 4919229, 318158, 375640, 478001, 974733, 650464, 791496, 88727, 1284130, 229758, 2272837], num_points=40960, test_area_idx=3, ignored_label_inds=[], ignored_objects=['wall', 'floor', 'ceiling', 'beam', 'column', 'clutter'], test_result_folder='./test', **kwargs)[source]#

Initialize the function by passing the dataset and other details.

Parameters:

  • dataset_path – The path to the dataset to use.

  • name – The name of the dataset (S3DIS in this case).

  • task – One of {segmentation, detection} for semantic segmentation and object detection.

  • cache_dir – The directory where the cache is stored.

  • use_cache – Indicates if the dataset should be cached.

  • class_weights – The class weights to use in the dataset.

  • num_points – The maximum number of points to use when splitting the dataset.

  • test_area_idx – The area to use for testing. The valid values are 1 through 6.

  • ignored_label_inds – A list of labels that should be ignored in the dataset.

  • ignored_objects – Ignored objects

  • test_result_folder – The folder where the test results should be stored.

static create_ply_files(dataset_path, class_names)[source]#
static get_label_to_names()[source]#

Returns a label to names dictonary object.

Returns:

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

get_split(split)[source]#

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)[source]#
is_tested(attr)[source]#

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.

static read_bboxes(bboxes, ignored_objects)[source]#
save_test_result(results, attr)[source]#

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.