* 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

* update PicoDet docs

* 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

* add LiteHRNet backbone and config .YML

* test lite18-network param

acc is same with ori-model 1. fix default darkpose=ON, 2. += is not inplace

add new keypoint model Lite-HRNet

* add new keypoint model Lite-HRNet

* 1. Add description of network type; 2. use channel_shuffle in ops.py

* use normal to init conv2d

* add network type description

* add gfl model and PicoDet

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

* add fairmot

* rename pretrain_weights

* add comments; reuse focal loss and convnorm

* update comments

* jde and deepsort: model

rename all Hrnet to HRNet

* update ssd loss, make it faster test=develop

* update comments, test=develop

* ssd loss, fix bug when no object, text=develop

* add ppyolov2

* fix bugs and modify docs

* modify code and doc according to review

* fix bugs while resolving conflicts

* add pssdet model

* refine ppdet file name

* unify bbox_utils

* add Distill model
* add distill+prune

* add fcos ttfnet coment, update modelzoo

* fix ttfnet coment

* 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>

* 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

* warning when YOLOv3Loss.batch_size setting

* add batch_size in YOLOv3Loss for backward compatable.

* sync TrainReader.batch to global train_batch_size