* refine sync bn

* fix bugs of batch_norm

* fix bugs while deploying and modify BatchNorm to BatchNorm2D

* param_attr -> weight_attr in BatchNorm2D

* modify BatchNorm to BatchNorm2D

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

* Add DETR

* drop return_pad_mask in PadBatch

* fix bs=2 of FCOS

* fix bs=2 of ttfnet

* fix cascade deploy

* speedup by paddle.expand

* add solov2 enhance model

* jde fairmot export and video python infer

* rcnn bs>1

* delete redundant comments

* bs>1 for YOLO

* add model_zoo unittest

* add fairmot

* rename pretrain_weights

* add comments; reuse focal loss and convnorm

* update comments

* fix hsv randomaffine

* fix nms return_index

* fix gt_ide by tid_start_index

* jde and deepsort: model

* fix name of ConvNormLayer for fcos solov2

* fix name in other head convbn

* fix yolo name, fix ttf_head name, test=document_fix

* add ttfnet enhance

* add doc

* fix pafnet training

* add senet

* add annotations according to review

* update slim model

* fix skip quant

* add fcos ttfnet coment, update modelzoo

* fix ttfnet coment

* add blazeface & update rcnn modelzoo

* remove condition num_priors

* add gn head fpn, test=dygraph

* add gn for cascade

* update gn readme, test=dygraph

* update cascade, test=dygraph

* clean code, test=dygraph

* add cascade_rcnn, test=dygraph

* update according to reviews, test=dygraph

* support dy2static, test=dygraph

* fix RCNN dygraph to static

* fit for YOLOvd/PPYOLO/SSD

* 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

* add ppyolo in dygraph

* fix bugs

* modify configs

* polish docs, modify ema and add configs

* modify link of model

* fix bugs in ema

* modify code according to review

* modify minicoco configs

* add fcos dcn mstrain doc and config

* add dcn on resnet and head

* clean code

* 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 dygraph model, test=dygraph