* fix bs=2 of FCOS

* fix bs=2 of ttfnet

* fix cascade deploy

* speedup by paddle.expand

* 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

* fix not find dirent.h on windows

* using cv::glob replace fileststem, fileststem need std++17

* add mot keypoint unite python infer

* fix mot pose fps

* refine keypoint deploy

* fit video infer

* fix post process

* update comments for keypoint_batch_size

* fix warning when result is empty

* fix warning when result is empty

add dark deploy supported, mpii deploy supported;

* add mot score to txt results

* fix mot install typo

* add epoch for deepsort

* fix paddle no_grad

* deploy infer save image txt

* fix bug when benchmark=True

* split warmup and repeat

* add DarkPsoe support

* modify Top-Down bbox_file str to bbox.json

* jde fairmot export and video python infer

* support xpu inference

* Automatically set use_dynamic_shape

* fix image_shape in export_model

* fix batch_size when trt infer

* bs>1 for YOLO

* update 2.1 readme

* update en doc, test=document_fix

* update doc, test=document_fix
Co-authored-by: NGuanghua Yu <742925032@qq.com>

* update slim models and benchmark

* Add document about how to export ONNX model

* update det infer benchmark log

* Update README.md

* s2anet fix export and deploy

* remove redundant code

* fix cpp for s2anet deploy

* fix bug of get_categories

* rename poly_to_rbox to poly2rbox

* add some comment for function

* add inference benchmark