python softmax函数

最新推荐文章于 2023-11-05 15:47:14 发布

smart_hang

最新推荐文章于 2023-11-05 15:47:14 发布

阅读量8.6k

点赞数 7

分类专栏：数据分析 python

本文链接：https://blog.csdn.net/hfutzhouyonghang/article/details/81630710

版权

python 同时被 2 个专栏收录

28 篇文章 0 订阅

订阅专栏

数据分析

14 篇文章 1 订阅

订阅专栏

数学公式

$\text{对于 } x \in \mathbb{R}^{1\times n} \text{, } softmax(x) = softmax(\begin{bmatrix} x_1 && x_2 && … && x_n \end{bmatrix}) = \begin{bmatrix} \frac{e^{x_1}}{\sum_{j}e^{x_j}} && \frac{e^{x_2}}{\sum_{j}e^{x_j}} && ... && \frac{e^{x_n}}{\sum_{j}e^{x_j}} \end{bmatrix}$
$\text{对于一个矩阵 } x \in \mathbb{R}^{m \times n} \text{, $x_{ij}$表示$x$的第 $i^{th}$行与第 $j^{th}$列,我们有: }$
$s o f t m a x (x) = s o f t m a x ⎡ ⎣ ⎢ ⎢ ⎢ ⎢ ⎢ x 11 x 21 ⋮ x m 1 x 12 x 22 ⋮ x m 2 x 13 x 23 ⋮ x m 3 \dots \dots ⋱ \dots x 1 n x 2 n ⋮ x m n ⎤ ⎦ ⎥ ⎥ ⎥ ⎥ ⎥ = ⎡ ⎣ ⎢ ⎢ ⎢ ⎢ ⎢ ⎢ ⎢ ⎢ e x 11 \sum j e x 1 j e x 21 \sum j e x 2 j ⋮ e x m 1 \sum j e x m j e x 12 \sum j e x 1 j e x 22 \sum j e x 2 j ⋮ e x m 2 \sum j e x m j e x 13 \sum j e x 1 j e x 23 \sum j e x 2 j ⋮ e x m 3 \sum j e x m j \dots \dots ⋱ \dots e x 1 n \sum j e x 1 j e x 2 n \sum j e x 2 j ⋮ e x m n \sum j e x m j ⎤ ⎦ ⎥ ⎥ ⎥ ⎥ ⎥ ⎥ ⎥ ⎥ = ⎛ ⎝ ⎜ ⎜ ⎜ ⎜ s o f t m a x (first row of x) s o f t m a x (second row of x) . . . s o f t m a x (last row of x) ⎞ ⎠ ⎟ ⎟ ⎟ ⎟$ $softmax(x) = softmax\begin{bmatrix} x_{11} & x_{12} & x_{13} & \dots & x_{1n} \\ x_{21} & x_{22} & x_{23} & \dots & x_{2n} \\ \vdots & \vdots & \vdots & \ddots & \vdots \\ x_{m1} & x_{m2} & x_{m3} & \dots & x_{mn} \end{bmatrix} = \begin{bmatrix} \frac{e^{x_{11}}}{\sum_{j}e^{x_{1j}}} & \frac{e^{x_{12}}}{\sum_{j}e^{x_{1j}}} & \frac{e^{x_{13}}}{\sum_{j}e^{x_{1j}}} & \dots & \frac{e^{x_{1n}}}{\sum_{j}e^{x_{1j}}} \\ \frac{e^{x_{21}}}{\sum_{j}e^{x_{2j}}} & \frac{e^{x_{22}}}{\sum_{j}e^{x_{2j}}} & \frac{e^{x_{23}}}{\sum_{j}e^{x_{2j}}} & \dots & \frac{e^{x_{2n}}}{\sum_{j}e^{x_{2j}}} \\ \vdots & \vdots & \vdots & \ddots & \vdots \\ \frac{e^{x_{m1}}}{\sum_{j}e^{x_{mj}}} & \frac{e^{x_{m2}}}{\sum_{j}e^{x_{mj}}} & \frac{e^{x_{m3}}}{\sum_{j}e^{x_{mj}}} & \dots & \frac{e^{x_{mn}}}{\sum_{j}e^{x_{mj}}} \end{bmatrix} = \begin{pmatrix} softmax\text{(first row of x)} \\ softmax\text{(second row of x)} \\ ... \\ softmax\text{(last row of x)} \\ \end{pmatrix}$

代码

def softmax(x):
    x_exp = np.exp(x)
    #如果是列向量，则axis=0
    x_sum = np.sum(x_exp, axis = 1, keepdims = True)
    s = x_exp / x_sum    
    return s

smart_hang

关注

7
点赞
踩
13

收藏

觉得还不错? 一键收藏
1
评论
python softmax函数

数学公式对于&amp;nbsp;x∈R1×n,&amp;nbsp;softmax(x)=softmax([x1x2…xn])=[ex1∑jexjex2∑jexj...exn∑jexj]对于&amp;nbsp;x∈R1×n,&amp;nbsp;softmax(x)=softmax([x1x2…xn])=[ex1∑jexjex2∑jexj...exn∑jexj] \text{对于 } x \in \mathbb{R}^{1\t...
复制链接

扫一扫

专栏目录