Multi-Concept Standard dataset

torchmil.datasets.MCStandardMILDataset

Bases: Dataset

Multi-Concept Standard MIL Dataset. Implementation from Algorithm 2 in Reproducibility in Multiple Instance Learning: A Case For Algorithmic Unit Tests.

__init__(D, num_bags, pos_class_prob=0.5, train=True, seed=0)

Parameters:

• D (int) –

  Dimensionality of the data.

• num_bags (int) –

  Number of bags in the dataset.

• pos_class_prob (float, default: 0.5 ) –

  Probability of a bag being positive.

• train (bool, default: True ) –

  Whether to create the training or test dataset.

• seed (int, default: 0 ) –

  Seed for the random number generator.

__getitem__(index)

Parameters:

• index (int) –

  Index of the bag to retrieve.

Returns:

• bag_dict ( TensorDict ) –

  Dictionary containing the following keys:

  • X: Bag features of shape (bag_size, feat_dim).
  • Y: Label of the bag.
  • y_inst: Instance labels of the bag.