* Create singan.md

* Create gradient_penalty.py

* add GradientPenalty

* add images for singan document

* add SinGANModel

* add SinGANGenerator

* add SinGANDiscriminator

* Create discriminator_singan.py

* Create generator_singan.py

* Create singan_model.py

* Create empty_dataset.py

* add EmptyDataset

* Create singan_predictor.py

* add SinGANPredictor

* Create singan.py

* create configs for singan

* add inference for singan

* create tipc config for singan

* Create python_singan_results_fp32.txt

* add tipc prepare for singan

* Update test_train_inference_python.md

* Update readme.md

* Update singan.md

* Update singan_model.py

* Update prepare.sh

* Update train_infer_python.txt

* Update prepare.sh

* Revert "add images for singan document"

This reverts commit f45fe5e55a2588611d951ae84d776c90693788df.

* Update singan.md

* update path format in configs

* update year of copyright

* modify the order of import

* Update singan_predictor.py

* update configs for singan

* Update singan_model.py

* modify urls for singan in prepare.sh

* add pretrained weight for singan

* Update singan_model.py

* Update singan.md

* Create English tutorial for SinGAN

* fix lapstyle input

* fix image path

* fix image path

* fix image path

* add mpr predictor and doc

* add doc

* fix result

* fix Results

* fix copyright

* add recurrent vsr predictor
* update docs

* add photopen 

* update photopen.md

* fix photopen_model.py

* fix the ci problem
Co-authored-by: Nqingqing01 <dangqingqing@baidu.com>

* fix benchmark

* fix fom mobile model

* add fom mobile

* add fom mobile

* add fom mobile

* add fom mobile

* fix  copyright

* fix  copyright 2

* fix  copyright 3

* add compress network of fom

* add stargan pretrain model

* 1.add face enhancement. 2.fix edge problem

* 1.add face enhancement. 2.fix edge problem

* 1.add face enhancement. 2.fix edge problem

* 1.add face enhancement. 2.fix edge problem

* 1.add face enhancement. 2.fix edge problem

* 1.add face enhancement. 2.fix edge problem

* 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

* 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