* add fitting module for styleganv2 and format some related codes

* add lapstyle predictor

* add docs

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

* delete cache files

* update gitignore

Change 'proccess' to 'process'

* 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

* Update mai-ha-hi related content

* Change description of first order motion model

* Add education project

* Update README.md
Co-authored-by: NLaraStuStu <lvxueying1991@foxmail.com>

* add blazeface detector

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

* add automatic weight download

* add wav2lip trainning code

* add stylegan2 and pixel2style2pixel models, predictors and documents

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

* refine codes docs

* fix pix2pix to_tensor

* fix apps

* add face_parse predictor in apps

* add art model of deoldify

* update psgan pretrained model link in the tutorial doc

* add video restore tutorial