pandas 中的标签平滑(软目标) [英] Label smoothing (soft targets) in Pandas

问题描述

在Pandas中，有 get_dummies 方法一键编码分类变量.现在，我要按照深度学习书的第7.5.1节中所述进行标签平滑:

In Pandas there is get_dummies method that one-hot encodes categorical variable. Now I want to do label smoothing as described in section 7.5.1 of Deep Learning book:

标签平滑通过将硬 0 和 1 分类目标替换为<eps / k和1 - (k - 1) / k * eps.

Label smoothing regularizes a model based on a softmax with k output values by replacing the hard 0 and 1 classification targets with targets of eps / k and 1 - (k - 1) / k * eps, respectively.

在Pandas数据框中进行标签平滑处理的最有效和/或最优雅的方法是什么?

What would be the most efficient and/or elegant way to do label smothing in Pandas dataframe?

推荐答案

首先，让我们使用更简单的方程式(ϵ表示您从真实标签"移动并分配给所有剩余标签的概率质量).

First, lets use much simpler equation (ϵ denotes how much probability mass you move from "true label" and distribute to all remaining ones).

1 -> 1 - ϵ
0 -> ϵ / (k-1) 

您只需使用上面的数学特性即可，因为您所要做的就是

You can simply use nice mathematical property of the above, since all you have to do is

x -> x * (1 - ϵ) + (1-x) * ϵ / (k-1)

因此，如果您的虚拟列是a, b, c, d，那么就做

thus if your dummy columns are a, b, c, d just do

indices = ['a', 'b', 'c', 'd']
eps = 0.1
df[indices] = df[indices] * (1 - eps) + (1-df[indices]) * eps / (len(indices) - 1)

为此

>>> df
   a  b  c  d
0  1  0  0  0
1  0  1  0  0
2  0  0  0  1
3  1  0  0  0
4  0  1  0  0
5  0  0  1  0

返回

        a         b         c         d
0  0.900000  0.033333  0.033333  0.033333
1  0.033333  0.900000  0.033333  0.033333
2  0.033333  0.033333  0.033333  0.900000
3  0.900000  0.033333  0.033333  0.033333
4  0.033333  0.900000  0.033333  0.033333
5  0.033333  0.033333  0.900000  0.033333

符合预期.

这篇关于 pandas 中的标签平滑(软目标)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！