pyabsa.networks.losses.LDAMLoss

Classes

LDAMLoss

References:

Module Contents

class pyabsa.networks.losses.LDAMLoss.LDAMLoss(cls_num_list, max_m=0.5, weight=None, s=30)

Bases: torch.nn.Module

References: Cao et al., Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss. NeurIPS 2019.

Parameters:

• s (float, double) – the scale of logits, according to the official codes.

• max_m (float, double) – margin on loss functions. See original paper’s Equation (12) and (13)

Notes: There are two hyper-parameters of LDAMLoss codes provided by official codes,

but the authors only provided the settings on long-tailed CIFAR. Settings on other datasets are not avaliable (https://github.com/kaidic/LDAM-DRW/issues/5).

m_list

s = 30

weight = None

cross_entropy

forward(x, target)