* refactor s2anet to support batch_size > 1

* fix problem of inference

* support batch_size > 1 for training

* fix empty results

* fix dota eval

* fix configs of s2anet_head

* modify s2anet_spine_1x to 73 mAP

* clean fluid

* mv static to legacy

* remove yolo box

* revert legacy dir

* revert static link

* update in_dynamic_mode

* clean iou_similarity, collect_fpn_proposals, bipartite_match

* fix mosaic in voc dataset

* fix is_crowd

* fix yaml constructor in eval & export

* fix typo

* add yolox doc and configs

* fix bn and update doc, test=document_fix

* fix infer dataset download and label

* add doc, test=document_fix

Fixed a possible error on line 2021: "TypeError: 'numpy.float64' object cannot be interpreted as an integer".

* [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 mcfairmot 4 class vehicle with bytetracker

* update modelzoo, test=document_fix

* add multi-scale test

* add resnet34-fpn-mstest item in model zoo

* fix label_list for mot, add warnings

* add result txt format, test=document_fix

* fix readme of mtmct, fix paddle.disable_static, test=document_fix

* remove paddle api

* fix problem of s2anet while deploying

* correct problem of s2anet TestReader

* add dota default category

* fix Momentum and label list

* fix export of mcfairmot

* update citation

* update citation

* 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 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