From 01839ad518ea84d3637a9622c4ac5a396107d570 Mon Sep 17 00:00:00 2001
From: SunGaofeng <peakbee@gmail.com>
Date: Fri, 5 Apr 2019 12:32:41 +0000
Subject: [PATCH] fix math format

---
 PaddleCV/video/models/nonlocal_model/README.md | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/PaddleCV/video/models/nonlocal_model/README.md b/PaddleCV/video/models/nonlocal_model/README.md
index 3550b531..d7b416d2 100644
--- a/PaddleCV/video/models/nonlocal_model/README.md
+++ b/PaddleCV/video/models/nonlocal_model/README.md
@@ -21,8 +21,7 @@ Non-local Neural Networks是由Xiaolong Wang等研究者在2017年提出的模
 
 Nonlocal 关联函数的定义如下
 
-<script type="text/javascript" src="http://cdn.mathjax.org/mathjax/latest/MathJax.js?config=default"></script>
-$$y_i=\frac{1}{C(x)}\sum{f(x_i, x_j)g(x_j)}$$
+<a href="https://www.codecogs.com/eqnedit.php?latex=y_{i}=\frac{1}{C(x)}&space;\sum_{j}f(x_i,&space;y_j)g(y_j)" target="_blank"><img src="https://latex.codecogs.com/gif.latex?y_{i}=\frac{1}{C(x)}&space;\sum_{j}f(x_i,&space;y_j)g(y_j)" title="y_{i}=\frac{1}{C(x)} \sum_{j}f(x_i, y_j)g(y_j)" /></a>
 
 在上面的公式中，x表示输入feature map， y表示输出feature map，i是输出feature map的位置，j是输入feature map的位置，f(yi, xj)是输出点和输入点之间的关联性的函数，C是根据f(yi, xj)选取的归一化函数。g(xj)是对输入feature map做一个变换操作，通常可以选取比较简单的线性变换形式；f(yi, xj)可以选取不同的形式，通常可以选择
 
-- 
GitLab