* [cherry_pick] [ppyoloe-plus] add task reademe and base config, test=document_fix (#6722)

* fix dy2static, use isinstance to avoid TensorArray transform (#6877)

* add gt as proposals for cascade
Co-authored-by: Nxiongkun <807377414@qq.com>

* multi_thread & multi_rtsp input (#6834)

* multi_thread & multi_rtsp input; test=document_fix

* update rtsp docs; test=document_fix

* update savename,add threadid to name;test=document_fix

* update pphuman&ppvehicle configs relative path

* add flag loss_normalize_pos

* add faster vitdet

* update faster vitdet

* update pphuman model of keypoint\attribute\action recognition

* update jetson docs

* mv yolov3 pedestrian to pphuman

* update ppvehicle&human det

* update links

* add vehicle plate & attribute

* add pphuman json & ppvehicle json

* fix some bugs and polish docs

* polish docs

* modify develop to release/2.5

* modify docs, test=document_fix

* modify docs, test=document_fix

* fix slice_infer

* fix doc, test=document_fix

* refactor rbox

* modify the code of save results

* fix some problem

* add .gitignore in dataset/dota

* fix test anno path

* add layout

* add layout

* [dev] add ppyoloe_plus configs and alter NormalizeImage

* alter other NormalizeImage

* alter cpp NormalizeImage

* add slice infer for smalldet

* add slice infer for smalldet

* fix slice infer

* fix doc, test=document_fix

* fix eval and configs

* add slice dataset loader

* fix deploy

* fix docs, test=document_fix

* update docs, test=document_fix

* add picodet full quant demo

* fix reader

* fix docs

* add picodet-npu model

* fix modelingf

* refactor s2anet to support batch_size > 1

* fix problem of inference

* support batch_size > 1 for training

* fix empty results

* fix dota eval

* fix configs of s2anet_head

* modify s2anet_spine_1x to 73 mAP

* update model pretrained links

* ppvehicle tutorials template

* rename pphuman docs

* update quickstart

* Update README.md

* Update README_en.md

* Update README_en.md

readme add infer result

* optimize lite doc

* add tinypose-enhance doc

* add coco result and rename picodet-model

* add flops & params

* update Q-code image for poseapp

* [smalldet visdrone] add modle zoo

* delete

* [smdet] add visdrone sliced config

* fix visdrone smalldet doc, test=document_fix

Signed-off-by: Ndaquexian <daquexian566@gmail.com>

* [Dy2St]Fix cascade_rcnn export model problem (#6468)

* [Dy2St]Fix cascade_rcnn export model problem

* [Dy2St]Fix cascade_rcnn export model problem

* fix import for mot

* fix import for mot deploy

* fix lazy import mot