1. Fix format of arguments
2. How to get model size
3. Add FAQ for compress other model

This is lbam model for picture inpainting

* add line space in PaddleVideo README

* add authors information for ets and tall

* fix shufflenet v2 bug

* Add project transfer info in README
* Update link in models/README.md for detection model

* sync 1.6

* sync 1.6

* update readme

* add log out for tall reader

* fix log info of tall reader

* update PaddleNLP  lexical_analysis for Release/1.6 (#3664)

* update for paddle 1.6

* update optimize op in paddle 1.6

* fix ernie based in paddle 1.6

* fix coding for windows

* update downloads.py (#3672)

* Fix infer bug on Release/1.6  

* fix bug on ernie based inferring

* replace open with io.open to be compatible with windows (#3707)

* update README.md

* update PaddleNLP emotion_detection and ernie for Release/1.6 (#3608)

* emotion-detection => 1.6

* ERNIE => 1.6

* [PaddleNLP] update emotion_detection readme

* [PaddleNLP] emotion_detection add download.py (#3649)

* emotion-detection => 1.6

* ERNIE => 1.6

* [PaddleNLP] update emotion_detection readme

* [PaddleNLP] emotion_detection add download.py for windows user

* [PaddleNLP] fix emotion_detection open problem, add paddlehub version (#3706)

* update emotion-detection readme and fix open problem

* fix ernie

* update DeepASR API and README

* update readme

* update README

* update simnet

fix typos in PaddleNLP/README.md

* fix fruit dataset

* fix md5

* update .run_ce.sh

* chmod +x .run_ce.sh

* add ce

* add ce

* add ce

* add ce

dv3: add trained model link for downloading

* move release 1.6 code to dev for tagging

* syn merged pr