* cherry-pick cfg modelzoo readme

* cherry pick modeling engine source

* cherry-pick deploy python mot

* update citation

* update citation

* add centernet

* add centernet

* add r50 for centernet

* support deploy for centernet

* add doc

* update pretrain

* clean code

* update r50 doc

* unify for_mot

* update code according to review

* update doc

* refine preprocess

* update doc

* set lr for 4 card as default, and update

Besides removing unnecessary imports, this also fixes the missing logger module in test_architectures.py within the static directory.

* add sparsercnn

* update sparsercnn

* Add DETR

* drop return_pad_mask in PadBatch

* add deepsort export model, reid infer

* fix jde_yolov3 metric

* fix deepsort deploy

* fix doc, clean code

* add mot deploy infer image, add run_benchmark

* refine keypoint deploy

* fit video infer

* fix post process

* update comments for keypoint_batch_size

* jde fairmot export and video python infer

* rcnn bs>1

* delete redundant comments

* bs>1 for YOLO

* add fairmot

* rename pretrain_weights

* add comments; reuse focal loss and convnorm

* update comments

* s2anet fix export and deploy

* remove redundant code

* fix cpp for s2anet deploy

* fix bug of get_categories

* rename poly_to_rbox to poly2rbox

* add some comment for function

* jde and deepsort: model

* add script of dota_2_coco

* add args for dota_to_coco

* add script to generate test result of dota

* add loss weight for s2anet

* fix dy2st for s2anet

* fix code style

* Add S2ANet model for Oriented Object Detection.

* add fcos ttfnet coment, update modelzoo

* fix ttfnet coment

* update cascade, test=dygraph

* clean code, test=dygraph

* add cascade_rcnn, test=dygraph

* update according to reviews, test=dygraph

* support dy2static, test=dygraph

* fix bbox_num 0 after nms, test=dygraph

* add copyright, test=dygraph

* fix RCNN dygraph to static

* fix problem due to empty bbox_pred and modify ppyolo docs, test=dygraph

* modify post process to avoid dy2st problem

* fix load_weight and no bbox output

* refactor rcnn, test=dygraph

* add mask_rcnn, test=dygraph

* add Faster RCNN & Faster FPN, test=dygraph

* update according to the review, test=dygraph

* ttfnet infer

* fix ttfnet deploy

* clean code

* add comment, fix config

* add comment, update modelzoo

* fix norm resize, update modelzoo

* fcos infer

* fcos training

* fix stgraph fcosloss

* fcos doc

* fix dy_fcos

* add comment

* train eval deploy fcos

* remove fcos config, add comment

* fix iter_tic
Co-authored-by: Nnemonameless <nemonameless@qq.com>
Co-authored-by: Ngeorgenemo <nifeng@pku.edu.cn>

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>