* fix picodet error in det_keypoint_unite_infer

* Optimize configuration file path

* fix naive-lite-hrnet backbone

* add WiderNaive-18 model

* add keypoint top-down cpp infer; total:5ms,pre:0.7ms,infer:3.8ms,post:0.01ms

* add dark_pose support

Revert "add keypoint top-down cpp infer; total:5ms,pre:0.7ms,infer:3.8ms,post:0.01ms (#4058)" (#4216)

This reverts commit 08619b4e.

* add LiteHRNet backbone and config .YML

* test lite18-network param

acc is same with ori-model 1. fix default darkpose=ON, 2. += is not inplace

add new keypoint model Lite-HRNet

* add new keypoint model Lite-HRNet

* 1. Add description of network type; 2. use channel_shuffle in ops.py

* use normal to init conv2d

* add network type description

* add --save_prediction_only support for TopDown KeyPoint Metric

* add a use case for save_prediction_only

* merge upstream

* clean code

* add batch_size in keypoint_detector

* add document for keypoint dataset preparation

* test=document_fix

* test=document_fix

* 关键点文档中json示例格式化显示，test=document_fix

* add mot keypoint unite python infer

* fix mot pose fps

add dark deploy supported, mpii deploy supported;

add config dark_hrnet_w32_384x288.yml;
test=document_fix;

* add DarkPsoe support

* modify Top-Down bbox_file str to bbox.json

* support no label training

* fix load_crowd

* update to fit rbox

* add empty_ratio

* update configs

* support mask rcnn

* clean drop_empty for mot & keypoint

* refine is_crowd