* support rcnn onnx

* clean code

* update cascade rcnn

* add todo for rpn proposals

* support nms options when export model

* fix config

* Add PP-YOLOE yaml

* rename PP-YOLOE

* Add exclude_nms in ppyoloe_head

* rename pretrain_weights

* [ppyolov3] add ppyolov3 base code

* add ppyolov3 s/m/x

* modify ema

* modify code to convert onnx successfully

* support arbitrary shape

* update config to use amp default

* refine ppyolo_head code

* modify reparameter code

* refine act layer

* adapter pico_head and tood_head code

* remove ppyolov3 yaml

* fix codestyle
Co-authored-by: Nwangxinxin08 <wangxinxin08@baidu.com>

* add a new version code of PicoDet

* add implementation of RetinaNet

* * add README.md and model zoo
* rename FOCSFeat -> RetianFeat
* add mstrain model to model zoo
* refactor DeltaBBoxCoder

* update link for model and log

* fix problem of s2anet while deploying

* correct problem of s2anet TestReader

* add dota default category

* add mcfairmot train eval export code

* fix eval and export

* update modelzoo

* add hrnet18_dlafpn

* unify jdetracker

* fix deploy infer for single class

* fix multi class fairmot deploy

* fix mcmot data source and deploy

* fix num_identities

* fix num_identities_dict

* add sge attention on fpn

* add iou head

* add config, fix head

* fix iou offset weight

* fix fairmot centerhead

* 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

* update PicoDet Architecture and config

* update picodet inference deploy

* [dev] add TOOD

* fix link and notes

* replace ConvNormLayer

* Update PicoDet adn GFl

* set lr for 4 card as default, and update

* s2anet update

* remove np anchor

* add gfl model and PicoDet

* clean code of s2anet

* fix for paddle==2.1.0

* remove debug info

* update comment