pyabsa.networks.losses.ClassImblanceCE

Classes

ClassBalanceCrossEntropyLoss

Reference:

Module Contents

class pyabsa.networks.losses.ClassImblanceCE.ClassBalanceCrossEntropyLoss

Bases: torch.nn.Module

Reference: Cui et al., Class-Balanced Loss Based on Effective Number of Samples. CVPR 2019.

Equation: Loss(x, c) = frac{1-beta}{1-beta^{n_c}} * CrossEntropy(x, c)

Class-balanced loss considers the real volumes, named effective numbers, of each class, rather than nominal numeber of images provided by original datasets.

Parameters:

beta (float, double) – hyper-parameter for class balanced loss to control the cost-sensitive weights.

beta

class_balanced_weight

update(epoch)

Parameters:

epoch – int. starting from 1.