From ca3524e0c2371f4bccb6446b6673c4f4428a9176 Mon Sep 17 00:00:00 2001
From: yinhaofeng <1841837261@qq.com>
Date: Mon, 21 Sep 2020 12:46:33 +0000
Subject: [PATCH] readme

---
 models/rank/logistic_regression/readme.md | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/models/rank/logistic_regression/readme.md b/models/rank/logistic_regression/readme.md
index cd6ee716..84237b60 100644
--- a/models/rank/logistic_regression/readme.md
+++ b/models/rank/logistic_regression/readme.md
@@ -210,9 +210,8 @@ first_weights = fluid.layers.reshape(first_weights_re,shape=[-1, self.num_field]
 #### sigmoid层
 将离散数据通过embedding查表得到的值，与连续数据的输入进行相乘再累加的操作，合为一个整体输入。我们又构造了一个初始化为0，shape为1的变量，将其与累加结果相加一起输入sigmoid中得到分类结果。  
 在这里，可以将这个过程理解为一个全连接层。通过embedding查表获得权重w，构造的变量b_linear即为偏置变量b，再经过激活函数为sigmoid。
-```math
-Out=Act(\sum^{N-1}_{i=0}X_iW_i+b)
-```
+$$Out=Act(\sum^{N-1}_{i=0}X_iW_i+b)$$
+
 
 ```python
 y_first_order = fluid.layers.reduce_sum(first_weights * feat_value, 1, keep_dim=True)
-- 
GitLab