* update mbv3 ssdlite

* fix ssdlite link

* update speed

* update model size of blazeface nas_v2

* remove speed of retinanet

* update doc

* add config link in model zoo

* fix link error

* add anchor free

* code for cornernet

* add doc

* refine custom op

* refine code from review comments

* refine doc

* update doc

* update code

* add cornernet_squeeze_mixup_cosine config

* update code

* update code

* add iou aware module
* iouaware model zoo
* fix copyright

* add mobilenet v3 configs

* fix some comment

* fix memsize

* add yolov3_mobilenet_v3

* add multi-scale testing function in cascade rcnn clsaware architecture

* fix all documentation

* fix docs conf.py

* fix some error

* fix readthedocs

* add gcnet model : https://arxiv.org/abs/1904.11492

* Add GIOU loss.
* Add DIOU/CIOU loss.
* Change loss box type in bbox_head.py.
* Remove fuse_elewise_add_act_ops flag in train.py (Error may happen for elem_divbased on the flag).

* add res2net model

* modify yml files

* add res2net model zoo

* add hrnet model

* modify model zoo

* minor fix readme

* update readme in dirs

* minor fix softnms bug

* refine model zoo

* modify yml files

* modify pretrain names

* Add cascade_rcnn_cls_aware_r200_vd_fpn_dcnv2_nonlocal_softnms model on oidv5 and obj365.
* Add obj365 config annotation
* Update docs.

* move path to PaddleDetection repo in docs

* refine README

* add softnms, nonlocal, resnet200_vd_backbone
* add CBNet
* update model zoo

* update code & doc

* Update PaddleDetection README
* Fix some link

* Update PaddleDetection/README_cn.md
* Follow comments
* Small update

* Add benchmark (fps) in MODEL_ZOO doc

* add gn doc

* update model zoo doc

* Add cascade deformable mdoels
* Fix MODLE_ZOO.md

# Add VGG-SSD on VOC and COCO dataset.
# Add config and model zoo. 
# Refine bbox2out and draw_bbox:
    - Add bbox de-normalize in bbox2out function.
    - Remove bbox de-normalize in draw_bbox.

* add deformable models
* fix dcn v2
* fix log_iter

Add PaddleDetection docs & some model configs

* add voc_eval and yolo_darknet_voc

* add yolov3_darknet_voc in MODEL_ZOO

* fix default im_size

* fix MODEL_ZOO note

* fix is_bbox_normalized

* extract map to map_utils.py

* update yolov3_dorknet_voc mixup

* add yolov3_r34_voc

* add yolov3_mobilenet_v1_voc

* fix drop empty in VAL mode

* use cfg.num_classes

* assert metric valid

* enable difficulty can be None

* add comment for bbox_eval

* num_classes in retinanet