* 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

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

* change fluid.layers.data to fluid.data

* fix export_model doc

* Optimize data transforms for yolo training

* Simplify and add docstring

* Fix nolocal naming
* Fix `cb_resnet` as well

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

* add info for obj365 download

* update code & doc

to avoid cycle import when required packages are not installed

* change voc_loader

* add x2coco.py

* Update DATA.md

* Update DATA_cn.md

* fix the labelme2coco.py

* fix the labelme2coco.py

* remove actual_shape

* add fpn fix

* refine doc for transfer learning

* add face doc
* update face detection readme and add demo jpg

* refine download sh to py

* update QUICK_STARTED

* add multi-scale test

* add class aware sampling strategy
* remove redundancy code