pyabsa.framework.sampler_class.imblanced_sampler

Classes

ImbalancedDatasetSampler

Samples elements randomly from a given list of indices for imbalanced dataset

Module Contents

class pyabsa.framework.sampler_class.imblanced_sampler.ImbalancedDatasetSampler(dataset, labels: list = None, indices: list = None, num_samples: int = None, callback_get_label: Callable = None)

Bases: torch.utils.data.sampler.Sampler

Samples elements randomly from a given list of indices for imbalanced dataset

Parameters:

• indices – a list of indices

• num_samples – number of samples to draw

• callback_get_label – a callback-like function which takes two arguments - dataset and index

indices

callback_get_label = None

num_samples

weights

_get_labels(dataset)

__iter__()

__len__()