* refine attr vis & refine model_dir in config

* support model_dir in command line

* added OpenVINO fairmort tutorial

* added Chinese version Readme.

* removed unused code

* fix becnhmark,delete run_process_type

* fix

* fix benchmarkk

* fix mask_rcnn_r50_1x_coco benchmark

* fix benchmark

* support nms options when export model

* fix config

Fixed a possible error on line 2021: "TypeError: 'numpy.float64' object cannot be interpreted as an integer".

* add bytetrack yolov3 engine and deploy baseline

* fix bytetrack yolov3 configs

* fix cfgs tools

* fix tracker pred_dets

* fit pptracking jde sde infer

* rename cfgs, fix mot_sde_infer

* fix mot sde single class infer

* remove byte cfgs

* fix mtmct

* clean code

* refine pipeline visualize

* add fps vis

* refine vis when box is empty

* fix deepsort detectors cfgs, add ppyoloe

* modify yolov3 40e

* add ppyoloe mot17half modelzoo

* add resnet embedding reid

* remove fasterfpn picodet, fix nms for higher MOTA

* add mot17 yml

* fix _base_ cfgs

* fix doc

* fix becnhmark,delete run_process_type

* fix

* fix benchmarkk

* add pedestrian pipeline

* add pipe_timer

* Add PP-YOLOE yaml

* rename PP-YOLOE

* Add exclude_nms in ppyoloe_head

* rename pretrain_weights

* add mcfiarmot ptq

* update docs

* refactor det deploy

* refactor keypoint deploy

* fix solov2

* fit mot sde pipeline infer

* refine mot sde infer

* fit mot jde infer pipeline

* fit mot pose unite infer

* precommit for format

* refine keypoint detector name

* clean codes

* fix keypoint infer

* refine format
Co-authored-by: NFeng Ni <nemonameless@qq.com>

* [ppyolov3] add ppyolov3 base code

* add ppyolov3 s/m/x

* modify ema

* modify code to convert onnx successfully

* support arbitrary shape

* update config to use amp default

* refine ppyolo_head code

* modify reparameter code

* refine act layer

* adapter pico_head and tood_head code

* remove ppyolov3 yaml

* fix codestyle
Co-authored-by: Nwangxinxin08 <wangxinxin08@baidu.com>

del json config & preprocess