* Update QUICK_STARTED_cn.md (#1757)

fix typo

* cherry-pick #1757 and #1473, test=document_fix

* update v0.5 release note

* update some comments

* Add PrepareData-->SelectModel-->Train-->Eval-->Test-->Infer-->Slim-->Deploy document DetectionPipeline.md, test=document_fix

* update solov2 some detail

* fix check paddle version

* enhance voc to coco docs

* fix voc annotation float type

* unify log_smooth_windows and log_iter

test=develop

* remove duplicate log_iter

* remain mobile yml, since they are soft-link

test=develop

* add PrepareDataSet.md, test=document_fix

* update PrepareDataSet, test=document_fix

* update PrepareDataSet, test=document_fix

* Update CN README
* Change demo and update doc

Repalce fruit dataset with roadsign dataset, and update QUICK_STARTED, use PP-YOLO as demo, test=document_fix. (#1407)

* add roadsign_voc dataset and update FAQ

* Add roadsign_voc dataset, updatea FAQ.md, and add yolov3_voc and yolov3_coco config template files.

* remove configs/templates

* convert config template file to md file, update comment

* mv config annotation file to config_annotation.

* move to docs/advanced_tutorials/config_doc

* rename

* update style

* update 2019-->2020

* update yolov3_mobilenet_v1_roadsign.md

* addd preprocess as yolov3_reader

* remove yolov3_mobilenet_v1_roadsign.md and add yolov3_mobilenet_v1.md

* fix typo

* update INSTALL

* fix typo

* add demo image

* add use_gpu annotation

* fix link

* update style

* update style

* add install paddle

* use python3

* update INSTALL_cn.md

* update INSTALL_cn.md

* update INSTALL_cn.md

* fix typo

* v0.4.0 change log

* add PPYOLO
Co-authored-by: Nlongxiang <longxiang@baidu.com>

Fix PSS-DET and large-scale models' links

* update mbv3 ssdlite

* fix ssdlite link

fix oidv5 doc link

Add practical generic detection models containing 676 categories

* update speed

* update model size of blazeface nas_v2

* remove speed of retinanet

* update doc

add fleet training

* fix voc dataset and docs

* add custom datsset demo

Update rcnn param doc

Add image for visualdl board.

* update doc in transfer learning

* update doc

* Add libra-rcnn, GCNet and iou loss intro doc.