* add devices_num on reader

* refine capacity value

* refine bufsize

* add yolov3_mobilenet_v3

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

* export config file in export_model.py

* add custom label_list & dump_box

* add infer_cfg.yml & doc

* export label_list to inference config

* update PaddleTensor to ZeroCopyTensor

Add cosine decay lr strategy.

fix multi-scale def

* add autoaugment, which is validated on faster-rcnn

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

* refine transfer learn

* refine transfer learning doc

* Replace `switch` ops with `cond`

* Use func instead of lambda

* Update checkpoint to use paddle 1.7 API

* Add new checkpoint support to `load_and_fusebn`

* Make yapf happy

* enable data unittest

* exit1 in travis failed

* fix all documentation

* fix docs conf.py

* fix some error

* fix readthedocs

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

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

* 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

* 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).