cloudViewer.ml.torch.datasets.ShapeNet

class cloudViewer.ml.torch.datasets.ShapeNet(dataset_path, name='ShapeNet', class_weights=[2690, 76, 55, 1824, 3746, 69, 787, 392, 1546, 445, 202, 184, 275, 66, 152, 5266], ignored_label_inds=[], test_result_folder='./test', task='classification', **kwargs)

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

The ShapeNet dataset includes a large set of 3D shapes.

__init__(dataset_path, name='ShapeNet', class_weights=[2690, 76, 55, 1824, 3746, 69, 787, 392, 1546, 445, 202, 184, 275, 66, 152, 5266], ignored_label_inds=[], test_result_folder='./test', task='classification', **kwargs)

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 (ShapeNet in this case).

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

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

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

• task – The task that identifies the purpose. The valid values are classification and segmentation.

Returns:

The corresponding class.

Return type:

class

static get_label_to_names(task='classification')

Returns a label to names dictonary object depending on the task. The valid values for task for classification and segmentation.

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(attr)

Checks if a datum in the dataset has been tested.

Parameters:

attr – The attribute that needs to be checked.

Returns:

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

attribute is stored; 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 the attribute passed.

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