* add server side rcnn model, 62 fps with coco mAP 41.6% and 20fps with coco mAP 47.8%

* exit1 in travis failed

add libra rcnn, including
  * libra loss
  * libra fpn(bfp)
  * libra sampling

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

- 1.add cn docs
- 2.fix fddb evaluate
- 3.fix get_shrink
- 4.delete FLAGS.dataset_dir

* 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

* Fix nolocal naming
* Fix `cb_resnet` as well

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

* update code & doc

* remove actual_shape

* add fpn fix

* add multi-scale test

This reverts commit 36a2e65bb74fc8ec9d1720b3db798757b5c0d044.

* Add face detection configs and main code.
* Integration multi-scale evaluation.

* Add backbone and architecture for FaceBoxes and Blazeface.
* Add dataloader for WIDERFace dataset.

* add a global norm_type flag

* add group norm on fpn

* add gn on box head

* add faster rcnn fpn 50 gn config

* add mask branch norm

* update configs

# 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.

* standard SENet and add a warning in coco loader

* add deformable models
* fix dcn v2
* fix log_iter

* 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

* fix resnet for resnet34

* fix ResNet18 and ResNet34

* update modelzoo and fix configs

* fix configs

* fix resnet bn

* Rename object_detection to PaddleDetection
* Small fix for doc