* update solov2 some detail

* fix check paddle version

* update cpp build script

* rename document and update script

* set WITH_MKL=ON for pass CI

* set WITH_GPU=OFF and WITH_TENSORRT=OFF for pass CI

* add TX2 cpp build document and benchmark

* turn WITH_MKL=ON

* add tensorrt version

* set WITH_GPU=OFF for CI

* keep same as TX2_build

* add benchmark on win10 cpp finer, fix bug of _mkdir on windows VS2019 Release bulig

* win cpp use Predictor to inference

* 测试环境描述更加详细

* add enable_static()

* follow comments

* remove blank line

* modify cpp output path

* fix compile error

* modify docs for windows

* add android demo

* add solov2 model

* fix train batch size

* add solov2_r101_vd_fpn_3x

* fix batch size and update modelzoo

* refactor code of solov2

* fix deploy/python

fix compile error in code
modify code for inference

* deploy code support camera

* add PPYOLO
Co-authored-by: Nlongxiang <longxiang@baidu.com>

* fix voc dataset and docs

* add custom datsset demo

* python deploy add log
* deploy add log & benchmark
* Update infer.py

* Add TesnorRT support in cpp deployment
* Change putText style

* fix export_model doc link error

* sort out release/0.3 docs

* add new CHANGELOG

* add yolov4 in changelog