* refine code, add infer module

* update readme

* do not print stack frame when train process killed
* add note about VOT does not support windows platform!

* update vot code
* remove local.py generate step, add tracking gif to README
* fix word usage in readme
* add got10k download website
* add pip install paddlepaddle-gpu
* fix word usage

* First version for VOT models.
* Include SiamFC and ATOM.
* A unified architecture for ATOM and Siames series models.

* modify save and load to 1.7 api

* add func to load parm

* upgrade dcn and xdeepfm, change from all old save/load api to fluid.save and fluid.load
* test=develop

update new api for rrpn

Bias attr of square conv should be "False" rather than None during training mode.

* update1.7 save/load & fluid.data

* update datafeed to dataloader

remove the CUDA_VISIBLE_DEVICES

Fix some typos.

* PointNet++ and PointRCNN use new API

* fix load for yolo_dy

* fix cyclegan download

* fix parallel error for 1.7

* remove modification to run.sh

Co-authored-by: NXing Wu <wuxing03@baidu.com>

test=develop

* fix multi-card multi-process bug

* fix gru_dygraph

* fix mmoe doc

* add args

* fix bmn model implemented with dynamic graph mode

* fix eval.py and README to increase the model usability

* fix gru_dygraph

* fix mmoe doc

delete bak files for SemSegPaddle

* update README

* fix monopoly info

* add kdd2020-p3ac

* add kdd2020-p3ac

* update p3ac info

* fix ptb_lm for support cpu, test=develop

* fix bug for arg_parse, test=develop

* update readme.me, test=develop

* update README

* fix monopoly info

* add kdd2020-p3ac

* add kdd2020-p3ac