* add doc for keypoint development

* fold examples

* some advice

* update human gif & qrcode, test=document_fix

* update link, test=document_fix

* add cascade vitdet

* cascade vit

* fix for model export

* add vit cascade cfgs

* update ppdet docs & remove static code, test=document_fix

* add pphuman doc, test=document_fix

* update action doc, test=document_fix

* update activity, test=document_fix

cast dtype in load_pretrain_weight

* optimize pphuman action document

* add en doc

* add break in counting for pphuman

* fix break in doc and codes

* fix mot break in region, test=document_fix

* fix region_polygon and region_type, test=document_fix

* add tools for get_video_info, test=document_fix

* update attr docs

* update more

* update docs

* given inference model path, download model automatically

* encapsulate auto download model as a function

* given note that default model dir is download link

* change attr model download path to https://bj.bcebos.com/v1/paddledet/models/pipeline/PPLCNet_x1_0_person_attribute_945_infer.zip

* [smalldet]add xview sliced config

* [smalldet] add Dota and xview config

* [smalldet] add xview and dota config

* [smalldet] fix path of weight

* [smalldet] add readme

* add ocsort tracker

* add ocsort deploy

* merge develop

* fix ocsort tracker codes

* fix doc, test=document_fix

* fix doc, test=document_fix

* attribute docs update

* fix mtmct

* update docs

* update convnext yolox ppyoloe

* fix cfg pretrain weights

* fix pdparams

* add pphuman mot doc, test=document_fix

* add mot data tutorials, test=document_fix

* add stage_loss_weights

* add FGD distill code

* add configs

* add doc

* fix pretrain

* pre-commit

* fix ci

* fix readme

* fix readme

* fix ci

* fix param groups

* fix

* fix doc

* fix doc,test=document_fix

* fix params groups

* Update action.md

delete the step of change model name of fight recognition

* Update video_action_infer.py

get model path from model_dir without model name

* optimize action vis