备注

您正在阅读 MMClassification 0.x 版本的文档。MMClassification 0.x 会在 2022 年末被切换为次要分支。建议您升级到 MMClassification 1.0 版本，体验更多新特性和新功能。请查阅 MMClassification 1.0 的安装教程、迁移教程以及更新日志。

mmcls.models.SeesawLoss¶

class mmcls.models.SeesawLoss(use_sigmoid=False, p=0.8, q=2.0, num_classes=1000, eps=0.01, reduction='mean', loss_weight=1.0)[源代码]¶

Implementation of seesaw loss.

Refers to Seesaw Loss for Long-Tailed Instance Segmentation (CVPR 2021)

参数

use_sigmoid (bool) – Whether the prediction uses sigmoid of softmax. Only False is supported. Defaults to False.
p (float) – The p in the mitigation factor. Defaults to 0.8.
q (float) – The q in the compenstation factor. Defaults to 2.0.
num_classes (int) – The number of classes. Default to 1000 for the ImageNet dataset.
eps (float) – The minimal value of divisor to smooth the computation of compensation factor, default to 1e-2.
reduction (str) – The method that reduces the loss to a scalar. Options are “none”, “mean” and “sum”. Default to “mean”.
loss_weight (float) – The weight of the loss. Defaults to 1.0