Caffe CNN:用于分层分类的多个分层损失 [英] Caffe CNN: multiple hierarchical losses for hierarchical classification

问题描述

我熟悉如何在CNN中使用多重损失，而这些损失的所有标签都是相同的.

I am familiar with how to use multiple loss in a CNN while all the labels of these loss are identical.

我的情况是使用多个损失处理层次结构标签，如下图所示:

My case here is handling hierarchical labels using multiple losses, as shown in figure bellow:

loss1负责labelset1:{Sport，Food}.标签2的损失2:{排球，足球}，标签3的损失3:{比萨，面食，汉堡}.例如，样本A∈{运动，足球}，样本B∈{食品，汉堡}.

loss1 is responsible for labelset1:{Sport, Food}. loss2 for labelset2:{volley, soccer}, loss3 for labelset3:{Pizza, Pasta, burger}. For example, Sample A∈{sport, soccer}, sample B∈{food,burger}.

任何想法如何做到这一点?

Any ideas how to do this?

推荐答案

添加无关"标签，每个样本应具有三个标签.例如:{sports, volleyball, don't care}.
然后，您可以得到类型"SoftmaxWithLoss"的三个损失.对于这两个特定的损失，您应该在不在乎"标签上添加ignore_label.

Adding "don't care" lables, you should have three labels for each sample. For example: {sports, volleyball, don't care}.
Then you can have the three losses of type "SoftmaxWithLoss". For the two specific losses you should add ignore_label for the don't care labels.

这篇关于Caffe CNN:用于分层分类的多个分层损失的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！