* 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

* 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

* fit some detectors for deepsort

* fix configs and readme

* add tracked bbox score cls_id, fix deploy bugs

* add deepsort cfg score threshold

* fix deploy deepsorttracker, fix cfgs

* merge develop, fix format

* add pplcnet

* add pplcnet cfgs

* fix cfgs

* fix cfgs

* clean pplcnet code

* fix readme

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

* 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

* jde fairmot export and video python infer

* add fairmot

* rename pretrain_weights

* add comments; reuse focal loss and convnorm

* update comments

* add deepsort configs comments

* fix doc, add readme_cn

* fix doc

* jde and deepsort: model