* enable shared memory

* add VisualDL and save best_model

* add VisualDLWriter callback

* add yolov3 voc configs for dygraph

* simplify yolov3 darknet voc configs

* support num_classes shared from dataset config

* Fix the bug of export quantized inference model

* Fix the bug of export quantized inference model

* add blazeface & update rcnn modelzoo

* remove condition num_priors

* fix doc link, test=dygraph, test=document

* use scripts to build on windows flatform, test=dygraph

* Use new preproces OPs in deploy/infer.py, test=dygraph

* fix bug of image_shape can not set 2-dims, test=dygraph

* fix cpp build, test=dygraph

* set param target_size must be [h, w] in Resize function, test=dygraph

* fix bug, test=dygraph

* fix ssd output format (bbox: [N, 6], bbox_num: bbox_num), test=dygraph

* fix ssd prediction in cpp mode, test=dygraph

* add pedestrian and vehicle models

* add pedestrian and vehicle json

* modify pedestrian and vehicle configs

* modify docs and links, test=dygraph

* update faster modelzoo and config, test=dygraph

* update model link, test=dygraph

* add gn head fpn, test=dygraph

* add gn for cascade

* update gn readme, test=dygraph

* from_config hrnet, test=dygraph

* update hrnet modelzoo, test=dygraph

* fix crash bug when using cpp infer, test=dygraph

* update PaddleServing deploy, test=dygraph

* Update export_model.py

* Update export_model.py
Co-authored-by: Nqingqing01 <dangqingqing@baidu.com>

* update cascade, test=dygraph

* clean code, test=dygraph

* add cascade_rcnn, test=dygraph

* update according to reviews, test=dygraph

* support dy2static, test=dygraph

* fix bbox_num 0 after nms, test=dygraph

* add copyright, test=dygraph

* add fp16 and fleet api

* add instructions for fleet api and fp16

* modify example of fleet api

* modify docs of fleet api

* fix_quickstart_doc

* fix RCNN dygraph to static