fix deadlink, test=document_fix (#6815)

Author: jerrywgz

README_cn.md

@@ -414,7 +414,6 @@
 - [快速体验](docs/tutorials/QUICK_STARTED_cn.md)
 - [数据准备](docs/tutorials/data/README.md)
 - [PaddleDetection全流程使用](docs/tutorials/GETTING_STARTED_cn.md)
-- [自定义数据训练](docs/tutorials/CustomizeDataTraining.md)
 - [FAQ/常见问题汇总](docs/tutorials/FAQ)
 
 ### 进阶教程
@@ -447,7 +446,7 @@
     - [目标检测](docs/advanced_tutorials/customization/detection.md)
     - [关键点检测](docs/advanced_tutorials/customization/keypoint_detection.md)
     - [多目标跟踪](docs/advanced_tutorials/customization/pphuman_mot.md)
-    - [行为识别](docs/advanced_tutorials/customization/pphuman_action.md)
+    - [行为识别](docs/advanced_tutorials/customization/action_recognotion/)
     - [属性识别](docs/advanced_tutorials/customization/pphuman_attribute.md)
 
 ### 课程专栏

README_en.md

@@ -407,7 +407,6 @@ Please refer to [docs](deploy/pipeline/README_en.md) for details.
 - [Quick start](docs/tutorials/QUICK_STARTED_cn.md)
 - [Data preparation](docs/tutorials/data/README.md)
 - [Geting Started on PaddleDetection](docs/tutorials/GETTING_STARTED_cn.md)
-- [Customize data training]((docs/tutorials/CustomizeDataTraining.md)
 - [FAQ]((docs/tutorials/FAQ)
 
 ### Advanced tutorials
@@ -446,7 +445,7 @@ Please refer to [docs](deploy/pipeline/README_en.md) for details.
     - [Object detection](docs/advanced_tutorials/customization/detection.md)
     - [Keypoint detection](docs/advanced_tutorials/customization/keypoint_detection.md)
     - [Multiple object tracking](docs/advanced_tutorials/customization/pphuman_mot.md)
-    - [Action recognition](docs/advanced_tutorials/customization/pphuman_action.md)
+    - [Action recognition](docs/advanced_tutorials/customization/action_recognotion/)
     - [Attribute recognition](docs/advanced_tutorials/customization/pphuman_attribute.md)
 
 ### Courses

docs/tutorials/data/PrepareDetDataSet.md

@@ -29,7 +29,7 @@
 |     x1,y1,w,h      | (x1,y1)为左上角坐标，w为目标区域宽度，h为目标区域高度  |
 |     xc,yc,w,h    | (xc,yc)为目标区域中心坐标，w为目标区域宽度，h为目标区域高度  |  
 
-常见的目标检测数据集如Pascal VOC采用的`[x1,y1,x2,y2]` 表示物体的bounding box, COCO采用的`[x1,y1,w,h]` 表示物体的bounding box, Cformat](https://cocodataset.org/#format-data).
+常见的目标检测数据集如Pascal VOC采用的`[x1,y1,x2,y2]` 表示物体的bounding box, [COCO](https://cocodataset.org/#format-data)采用的`[x1,y1,w,h]` 表示物体的bounding box.
 
 ### 准备训练数据  
 

docs/tutorials/data/PrepareDetDataSet_en.md

@@ -27,7 +27,7 @@ The general object position is represented by a rectangular box, which is genera
 |  x1,y1,w,h  | (x1,y1)is the top left coordinate, w is width of object, h is height of object |
 |  xc,yc,w,h  |    (xc,yc)is center of object, w is width of object, h is height of object     |
 
-Common object detection datasets such as Pascal VOC, adopting `[x1,y1,x2,y2]` to express the bounding box of object. COCO uses `[x1,y1,w,h]` , [format](https://cocodataset.org/#format-data).
+Common object detection datasets such as Pascal VOC, adopting `[x1,y1,x2,y2]` to express the bounding box of object. COCO uses `[x1,y1,w,h]`, [format](https://cocodataset.org/#format-data).
 
 ### Prepare Training Data
 PaddleDetection is supported [COCO](http://cocodataset.org) and [Pascal VOC](http://host.robots.ox.ac.uk/pascal/VOC/) and [WIDER-FACE](http://shuoyang1213.me/WIDERFACE/) datasets by default.