* set lr for 4 card as default, and update

* add gfl model and PicoDet

* mot video decode to images

* add infer_dir for mot

* fix export and unite pose infer

* remove task in mot source

* set image_dir

* update doc

* fix tracker trt, add tracker to infer_cfg yml

* fix doc and deploy tracker

* jde fairmot export and video python infer

* Automatically set use_dynamic_shape

* fix image_shape in export_model

* fix infer bug of s2anet

* add inference benchmark

* Add BottomUp HigherHRNet for pose.
* reverse xtcocotools to pycocotools

* Add S2ANet model for Oriented Object Detection.

* refine trainer

* support not pad gt in rcnn model

* add comment in reader

* remove load_static_weights

* use scripts to build on windows flatform, test=dygraph

* Use new preproces OPs in deploy/infer.py, test=dygraph

* fix bug of image_shape can not set 2-dims, test=dygraph

* fix cpp build, test=dygraph

* set param target_size must be [h, w] in Resize function, test=dygraph

* fix bug, test=dygraph

* fix ssd output format (bbox: [N, 6], bbox_num: bbox_num), test=dygraph

* fix ssd prediction in cpp mode, test=dygraph

* fix RCNN dygraph to static

* refactor rcnn, test=dygraph

* add mask_rcnn, test=dygraph

* add Faster RCNN & Faster FPN, test=dygraph

* update according to the review, test=dygraph

* fix modelzoo link

* fix config, remove some faster mask modelzoo

* fix readme

* fix ssd mbv1 config

* fix trt infer

* ppdet installable

Merge dygraph branch into master branch.
Co-authored-by: NFDInSky <48318485+FDInSky@users.noreply.github.com>
Co-authored-by: Nsunxl1988 <47514455+sunxl1988@users.noreply.github.com>
Co-authored-by: Nwangguanzhong <jerrywgz@126.com>
Co-authored-by: Nwangxinxin08 <69842442+wangxinxin08@users.noreply.github.com>
Co-authored-by: Nwanghuancoder <wanghuancoder@163.com>
Co-authored-by: Ncnn <liuhui29@baidu.com>
Co-authored-by: NGuanghua Yu <742925032@qq.com>
Co-authored-by: NKaipeng Deng <dengkaipeng@baidu.com>
Co-authored-by: Nroot <root@bjyz-sys-gpu-kongming0.bjyz.baidu.com>