* fix bugs of multipeople inference

Co-authored-by: NLielinJiang <50691816+LielinJiang@users.noreply.github.com>

* fix doc errors

* fix 2.0-beta bugs

* update pretreained path

* add extract_weight.py

* fix some errors in test

* modified fluid to paddle API

* supplement zh_CN documents

* add wav2lip doc

* Add photo2cartoon model
* Resolve conflicts
* Remove comments
* Add photo2cartoon tutorial
* update p2c tutorials

* add stylegan2 and pixel2style2pixel models, predictors and documents

* Integrate with visualdl
* visualdl: add doc and control paramter
* visual dl: move import, add install doc

* Add MidDaSv2 in ppgan.apps
* remove ppgan/apps/midas/run.py

* Update README
* Remove ppgan/faceutils/dlibutils/lms.dat
* Update apps.md

* add animeganv2 network and dataset
* animegan:refine code,add License
Co-authored-by: Nqingqing01 <dangqingqing@baidu.com>

* fix import and docs

* docs: update install instruction

1. paddlepaddle2.0.0rc instruction can be found from main page
2. only two steps, install paddlepaddle and paddlegan, other than 3step

* docs: update en install
* feat: add dcgan
* reform: debug with mnist datset
validate performance with different options, and original structure and setting

* refine codes docs

* fix pix2pix to_tensor

* fix apps

* refine duplicate frames and fix some bugs

* add face_parse predictor in apps

* remove duplicate frames and keep timestamp, fix psgan docs

* add art model of deoldify

* update demo

* update psgan pretrained model link in the tutorial doc

* 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