From 36e8a1838f5fe8d8ee6cb47045c2e4ea623f17c2 Mon Sep 17 00:00:00 2001
From: Yulv-git <34329208+Yulv-git@users.noreply.github.com>
Date: Thu, 4 Aug 2022 11:25:18 +0800
Subject: [PATCH] Update KeyPoint Detection Readme for some typos and links.
 (#6581)

* Update README.md

* Update README_en.md

* Update README_en.md
---
 configs/keypoint/README.md    |  9 ++++-----
 configs/keypoint/README_en.md | 17 +++++------------
 2 files changed, 9 insertions(+), 17 deletions(-)

diff --git a/configs/keypoint/README.md b/configs/keypoint/README.md
index 685708a02..4ca9b0747 100644
--- a/configs/keypoint/README.md
+++ b/configs/keypoint/README.md
@@ -23,16 +23,15 @@
       - [Top-Down模型联合部署](#top-down模型联合部署)
       - [Bottom-Up模型独立部署](#bottom-up模型独立部署)
       - [与多目标跟踪联合部署](#与多目标跟踪模型fairmot联合部署)
-    - [完整部署教程及Demo](#4完整部署教程及Demo)
-
+    - [完整部署教程及Demo](#完整部署教程及Demo)
 - [自定义数据训练](#自定义数据训练)
 - [BenchMark](#benchmark)
 
 ## 简介
 
-PaddleDetection 关键点检测能力紧跟业内最新最优算法方案，包含Top-Down、Bottom-Up两套方案，Top-Down先检测主体，再检测局部关键点，优点是精度较高，缺点是速度会随着检测对象的个数增加，Bottom-Up先检测关键点再组合到对应的部位上，优点是速度快，与检测对象个数无关，缺点是精度较低。
+PaddleDetection 中的关键点检测部分紧跟最先进的算法，包括 Top-Down 和 Bottom-Up 两种方法，可以满足用户的不同需求。Top-Down 先检测对象，再检测特定关键点。Top-Down 模型的准确率会更高，但速度会随着对象数量的增加而变慢。不同的是，Bottom-Up 首先检测点，然后对这些点进行分组或连接以形成多个人体姿势实例。Bottom-Up 的速度是固定的，不会随着物体数量的增加而变慢，但精度会更低。
 
-同时，PaddleDetection提供针对移动端设备优化的自研实时关键点检测模型[PP-TinyPose](./tiny_pose/README.md)，以满足用户的不同需求。
+同时，PaddleDetection 提供针对移动端设备优化的自研实时关键点检测模型 [PP-TinyPose](./tiny_pose/README.md)。
 
 ## 模型推荐
 
@@ -184,7 +183,7 @@ python deploy/python/mot_keypoint_unite_infer.py --mot_model_dir=output_inferenc
 **注意:**
  跟踪模型导出教程请参考[文档](../mot/README.md)。
 
-### 4、完整部署教程及Demo
+### 完整部署教程及Demo
 
 
 ​ 我们提供了PaddleInference(服务器端)、PaddleLite(移动端)、第三方部署(MNN、OpenVino)支持。无需依赖训练代码，deploy文件夹下相应文件夹提供独立完整部署代码。 详见 [部署文档](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/deploy/README.md)介绍。
diff --git a/configs/keypoint/README_en.md b/configs/keypoint/README_en.md
index a7aa7a6c5..f6f049824 100644
--- a/configs/keypoint/README_en.md
+++ b/configs/keypoint/README_en.md
@@ -19,22 +19,15 @@
       - [Deployment for Top-Down models](#deployment-for-top-down-models)
       - [Deployment for Bottom-Up models](#deployment-for-bottom-up-models)
       - [Joint Inference with Multi-Object Tracking Model FairMOT](#joint-inference-with-multi-object-tracking-model-fairmot)
-  - [Complete Deploy Instruction and Demo](#4Complete-Deploy-Instruction-and-Demo)
-
-- [Train with custom data](#Train-with-custom-data)
-
+  - [Complete Deploy Instruction and Demo](#complete-deploy-instruction-and-demo)
+- [Train with custom data](#train-with-custom-data)
 - [BenchMark](#benchmark)
 
 ## Introduction
 
-The keypoint detection part in PaddleDetection follows the state-of-the-art algorithm closely, including Top-Down and Bottom-Up methods, which can satisfy the different needs of users.
-
-Top-Down detects the object first and then detect the specific keypoint. The accuracy of Top-Down models will be higher, but the time required will increase by the number of objects.
-
-
-Differently, Bottom-Up detects the point first and then group or connect those points to form several instances of human pose. The speed of Bottom-Up is fixed and will not increase by the number of objects, but the accuracy will be lower.
+The keypoint detection part in PaddleDetection follows the state-of-the-art algorithm closely, including Top-Down and Bottom-Up methods, which can satisfy the different needs of users. Top-Down detects the object first and then detects the specific keypoint. Top-Down models will be more accurate, but slower as the number of objects increases. Differently, Bottom-Up detects the point first and then group or connect those points to form several instances of human pose. The speed of Bottom-Up is fixed, it won't slow down as the number of objects increases, but it will be less accurate.
 
-At the same time, PaddleDetection provides [PP-TinyPose](./tiny_pose/README_en.md) specially for mobile devices.
+At the same time, PaddleDetection provides a self-developed real-time keypoint detection model [PP-TinyPose](./tiny_pose/README_en.md) optimized for mobile devices.
 
 <div align="center">
   <img src="./football_keypoint.gif" width='800'/>
@@ -195,7 +188,7 @@ python deploy/python/mot_keypoint_unite_infer.py --mot_model_dir=output_inferenc
 **Note:**
  To export MOT model, please refer to [Here](../../configs/mot/README_en.md).
 
-### 4.Complete Deploy Instruction and Demo
+### Complete Deploy Instruction and Demo
 
 ​ We provide standalone deploy of PaddleInference(Server-GPU)、PaddleLite(mobile、ARM)、Third-Engine(MNN、OpenVino), which is independent of training codes。For detail, please click [Deploy-docs](https://github.com/PaddlePaddle/PaddleDetection/blob/develop/deploy/README_en.md)。
 
-- 
GitLab