* add mpr deblur derain and denoise pretrained models for image restoration application

* 1.fix error with 4 channels of image of fom predictor. 2.fix error of fom evaluate 3.fix lapstyle vgg network

* test

* add training od first order motion

* Modify codes according to reviews

* Modify codes according to reviews

* (1)modify single person and multi person process of fom model. (2)git rid of sklearn, skimage

* modify documents of fom

* modify review code

* modify review code

* modify review code

* 1.add vox training; 2.fix attributed error for DataParallel. 3.fix fom fps

update fom docs

* add training od first order motion
* Modify codes according to reviews
* modify single person and multi person process of fom model. 
* Git rid of sklearn, skimage

* add blazeface detector

* update install docs

* fix windows bug

* fix download when in windows

* fix video2frames bug on windows platform

* fix windows bug

* fix bugs of multipeople inference

增加文件名的参数filename，以便可以多并发执行
first_order_predictor.py

* fix bugs

* fix some errors in test

* fix some errors in test

* fix errors in face parse

* fix some errors in test

* modified fluid to paddle API

* supplement zh_CN documents

* add dped docs

* add automatic weight download

* add wav2lip trainning code

* fix some bugs

* update configs

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

* add stylegan2 and pixel2style2pixel models, predictors and documents

* set en readme as default

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

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

* add ugatit model

* 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