* add video infer for TestMOTReader

* format, test=documment_fix

* add fairmot

* rename pretrain_weights

* add comments; reuse focal loss and convnorm

* update comments

* fix jde doc and metric test_mode

* add image_lists

* add readme_cn

* add config for jde and deepsort, add engine metric tools

* add mot_metrics

* fix configs engine and others

* fix configs others

* move configs

* fix ap_per_class, fix doc

* fix test_mode, seqs

* fix test_mode to metric

* fix JDE arch metric

* clean requirement

* add to requirement

* add mot data

* fix operators, source

* fix data source transform

* fix parse_dataset register_op

* fix scale_factor, RandomAffine

* add assert for check

* fix ci

* refine yolov3 configs

* fix dataset problem

* Add S2ANet model for Oriented Object Detection.