* refine duplicate frames and fix some bugs

* update readme

* add app apis

* add face_parse predictor in apps

* remove duplicate frames and keep timestamp, fix psgan docs

* update Readme

* add art model of deoldify

Made several changes:
- an -> a
- Realse->Release
- Traning ->Training
- Unify application with noun.

* update demo

* update psgan pretrained model link in the tutorial doc

* Update README.md
* put jpeg center

* Refine some docs
* Update docs/en_US/data_prepare.md

* Update README
* Change docs dir to en_US and zh_CN
* Add paper reference
* Fix link

* refine codes docs

* add psgan and fom tutorial doc

* add video restore tutorial

* Add doc for Apps and refine some code
* Add how to switch cpu and gpu

* add docs

* update

* refine code

* test

* fix apps

* update readme

* rm unused code

* fix apps output when input is image

* clean code

* update requirements.txt

* Add contribute doc
* Fix comments

update readme

fix some apis to paddle-dev

refine loss related code and align to the newest develop api