predict_image() requires that the image is RGB format, but VideoCapture.read() returns BGR image,
so we need to convert the frame to RGB format.

* fix npu tipc script

* fix typo

* fix conflict

* add npu inference support

* fix typo

* add ppyoloe_sod_qat

* ppyoloe sod qat

* add ppyoloe_sod qat demo

* fix ppyoloe sod qat yml

* add ppyoloe-sod ppyoloe_tiny qat

* add ppyoloe_sod_qat readme

* fix run_benchmark for small model accurate speed

* fix run_benchmark for other det models

* ppvehicle add customized docs, test=document_fix

* fix pipeline readme.md test=document_fix

* fix pipeline readme.md link test=document_fix

* add licensed to lane_to_mask.py

* ppvehicle_violation.md add args list test=document_fix

* update pipeline docs; vehicle illegal;rtsp;jetson

* update docs

* bold text

* update release 2.6 doc, test=document_fix

* update release/2.6 doc, test=document_fix

* ppvehicle_press ppvehicle_retrograde doc fix link  test=document_fix

* ppvehicle_press ppvehicle_retrograde doc abs path fix rel path  test=document_fix

* add ppyoloe architectures

* fix deploy ppyoloe arch

* add ppyoloe arch coments, test=document_fix

* pipeline.py add tracking module time
fix infer_cfg_vehicle_violation.yml for examples

* pipeline examples infer_cfg_vehicle_violation.yml delete irrelevant config

* fix infer_cfg_vehicle_violation.yml enable

* Add BOTSORTTracker
* pptracking/python/mot/tracker/botsort_tracker.py
* ppdet/modeling/mot/tracker/botsort_tracker.py

fix OCSORTTracker

* * botsort kalman_filter.py float64->float32
* requirements.txt add numba

* [Mot] kalman_filter.py lazy import numba
* add code source and modify comments

* [MOT] fix numba lazy import bug

* [MOT] botsort add README.md

* delete comment code

* add centertrack base codes

* fix deploy and docs

* fix tracker

* fix

* fix pre_img

* fix deploy

* fix

* * add vehicle_pressing.py to judge vehicle press lane
* add lane_seg_infer.py to lane seg
* add pipeline vehicle retrograde:
* add vehicle_retrograde.py to judge vehicle retrograde
* add infer_cfg_vehicle_violation.yml to config vehicle press vehicle retrograde
* add lane_seg_config.yml to config lane seg

* *add ppvehicle_press readme
*add ppvehicle_retrograde.md
*fix lane_seg preditor init

* ppvehicle_press.md ppvehicle_retrograde.ma add gif image

* *fix  ppvehicle press retrograde readme, test=document_fix
*add ppvehicle press retrograde en readme test=document_fix
*fix ppvehicle retrograde keep left bug

* fix ppvehicle readme,test=document_fix

* fix ppvehicle retrograde en readme,test=document_fix

* ppvehicle_press ppvehicle_retrograde readme add sulution test=document_fix

* fix ppvehicle press retrograde readme format test=document_fix

* fix dead links, test=document_fix

* fix docs, test=document_fix

* update doc, test=document_fix

* update en doc, test=document_fix

* update link, test=document_fix

* remove duplicate backbone variant, test=document_fix

* fix slice_image deploy infer index

* fix time count while less than warmupframe

* eliminate capture video time cost

* update PP-Vehicle docs and en docs

* add reid model in v2.5 modelzoo

* update more