influence.feeder

Feeding interface for Influence class

class InfluenceFeeder

Bases: object

reset()

reset dataset

test_indices(indices)

test data feeder

Parameters:indices (testing sample index) – Returns:

• x (feed input values)
• y (feed label values)

train_batch(batch_size)

training data feeder by batch sampling

Parameters:batch_size (batch size) – Returns:

• xs (feed input values)
• ys (feed label values)

train_one(index)

single training data feeder

Parameters:index (training sample index) – Returns:

• x (feed one input value)
• y (feed one label value)