* refactor dygraph & add mask rcnn fpn

* fix initialization & minor update

* refine architecture of mask_rcnn

add train&eval 
add reader padding 
add new config 

add cascade rcnn and modify make net method
add new cfg method 
add auto debug tool

add faster rcnn\mask\cascade rcnn model arch\module\op
add base debug func in bufferdict 

* add version check

* update version check & python version for cornerpool

* fix with_background in export model

* fix coco_eval background

* add yolov4

* Make logger less noisy

* Fix indent

* update check config

* fix slim/xx

* 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 yolov3_mobilenet_v3

* refine transfer learn

* refine transfer learning doc

* Update checkpoint to use paddle 1.7 API

* Add new checkpoint support to `load_and_fusebn`

* Make yapf happy

* exit1 in travis failed

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

* 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

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

* 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.

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

* add info for obj365 download

* update code & doc

* change voc_loader

* 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