* Scale frames before fight action recognition

* put
short_size = self.cfg["VIDEO_ACTION"]["short_size"]
scale = Scale(short_size)
out of while

* change class name from Scale to ShortSizeScale

* add fight for PP-Human

* add short_size and target_size for fight recognition

* add short_size and target_size for fight_infer

* modify code according to the reviews

* add the wrong deleted lines`

* Update pipeline.py

* Update infer_cfg.yml

* visualize fight when fight action occur

* 乱码修改

* delete useless parmas

* delete useless code str2bool

* fix video infer(#5107)

* fix video infer(others)

* save detection results to file using coco format

* update save docs

* change id to image path when save result of image directory prediction

* fix error info

* fix infer dataset download and label

* add doc, test=document_fix

* fix deploy python mot infer, fix cfgs

* fix doc, test=document_fix

* add nms trt support

* add check version code

* fix bugs

* support mask rcnn bs>2

* fix resize op in c++ deploy

* fix preprocess in mask rcnn

* fix cascade mask rcnn when box is empty

* update merge batch

* fix error when all bbox are filered

* remove filter in function get_person_from_rect

* 1. add timer for kpt& action 2. trt support for stgcn

* add parameter description

* make warm_frame configurable

* add keypoint infer and visualize into Pipeline

* add independent action model inference

* add action inference into pipeline, still in working

* test different display frames and normalization methods

* use bbox and scale normalization

* Remove debug info and Optimize code structure

* remove useless visual param

* make action parameters configurable

* add pphuman doc

* add pphuman doc & add enable_attr, enable_action

* update doc

* update pphuman-tech.png

* add mkldnn bfloat16 args

* add mkldnn_bfloat16 to static deploy

* update

* update

* refine attr vis & refine model_dir in config

* support model_dir in command line

* 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

* add pedestrian pipeline

* add pipe_timer

* 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>

* add keypoint benchmark data

* update benchmark-data and change default keypoint bs=8, to be same as C++ infer

* support rcnn bs=2 in cpp infer

* check dynamic shape in padbatch

* replace fluid by paddle

* fix time display in pptracking cpp

* fix timer in bs=2