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

* add iou loss to yolov3
* modify the comment and delete redundant yml file
* fix the low speed bug in dropblock module

* add slim model zoo

* update merge api
* add coco distillation demo
* fix details
* resolve some issues

* Add latency table
* Add latency demo
* Update doc

* add slim quantization demo

* add quantization demo

* add skip quant

* fix details in doc

* fix details

* fix details

* fix details

* fix details

* fix details

* fix details

* add model zoo link in doc

* remove result in doc

* add dropblock module
* move dropblock module from yolo_head to ops
* fix obj365 num classes

* add blazeface nas demo

* fix format

* fix configs

* fix reduce_rate

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

* refine code & doc for cpp_infer

* add cython for pycocotools install

* add diou nms.
* fix typo in diou nms and soft nms (lod_leval->lod_level).

* update distillation demo

* load inference

* add doc

* add config file for tensorrt_infer

* add padding for rcnn preprocess

* refine code & doc

* refine cocoapi import

* fix infer when anno_path is None

`--minimal` is option for `generate` and should be positioned after it

* 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).

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

* split yolov3 loss

* add step in prior_box

* refine README

* 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

* Polish Reader to simplify preprocessing logic.
#  sample_transforms-> make batch -> batch_transforms in Reader.
* Clean some code
* Imporve yolov3_r50vd_dcn_obj365_pretrained_coco 41.4 to 41.8.
* Update all configs.

* Update x2coco.py to fix the cityscape bug when split dataset  

Fix hang bug in parallel_map.py when multiprocessing mode used and some consumer exit abnormally (#106)

so that it does not choke on non conforming docstrings

* Update GETTING_STARTED_cn.md
* Update x2coco.py

* fix mixup error when dataset has only 1 sample

* refine log