Semi-supervised learning

Collection of utilities for semi-supervised learning where some part of the data is labeled and the other part is not.

---

Balanced classes

Example:

from pl_bolts.utils.semi_supervised import balance_classes

pl_bolts.utils.semi_supervised.balance_classes(X, Y, batch_size)

Makes sure each batch has an equal amount of data from each class. Perfect balance.

Parameters

• X (Union[Tensor, ndarray]) – input features

• Y (Union[Tensor, ndarray, Sequence[int]]) – mixed labels (ints)

• batch_size (int) – the ultimate batch size

Return type

Tuple[ndarray, ndarray]

half labeled batches

Example:

from pl_bolts.utils.semi_supervised import balance_classes

pl_bolts.utils.semi_supervised.generate_half_labeled_batches(smaller_set_X, smaller_set_Y, larger_set_X, larger_set_Y, batch_size)

Given a labeled dataset and an unlabeled dataset, this function generates a joint pair where half the batches are labeled and the other half is not.

Return type

Tuple[ndarray, ndarray]