open3d.ml.tf.datasets.ShapeNet¶
-
class
open3d.ml.tf.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 dictionary 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.
-