torch_concepts.data.datasets.mnist.PartialMNISTAddition¶

class PartialMNISTAddition(root, train, target_transform=None, download=True)[source]¶

The partial MNIST addition dataset is a modified version of the MNIST addition dataset where the concept annotation is partial. The concept associated with the second digit is not provided.

__init__(root, train, target_transform=None, download=True)¶

Methods

`__init__`(root, train[, target_transform, ...])
`download`()	Download the MNIST data if it doesn't exist already.
`extra_repr`()

Attributes

`class_to_idx`
`classes`
`concept_names`
`input_dim`
`input_shape`
`mirrors`
`n_concepts`
`n_tasks`
`name`
`processed_folder`
`raw_folder`
`resources`
`task_names`
`test_data`
`test_file`
`test_labels`
`train_data`
`train_labels`
`training_file`
`transform`