* add cascade mask

* add cascade rcnn

* update code

* remove comments

* add Mask R-CNN model

* fix mask rcnn eval

* fix mask rcnn infer

* fix mask rcnn config

* fix infer config

* add export_model and deploy

* fix travis-ci

* update CMakeList & linux doc

* update by comments

* adapt new im_shape im Mask R-CNN-FPN

* fix training

* split yolov3 loss using paddle op

* add sync_bn and modify list to LayerList to use sync_bn, add missing op, support cutmix op in dataset, modify reader to use new ops

* modify code according to review

* modify code to run eval.py successfully

* modify code to run eval and train successfully

* modify code to use mixup

* rebase code on lastest dygraph

* modify code to run in sync_bn mode

* modify code according to review

* modify target size of ResizeOp

* update YOLOv3 config

* add matrix nms api

* add test error in matrix nms ut

* modify code according to review

* modify matrix nms api

* migrate roi_align and roi_pool to ops

* modify code according to review

* migrate detection ops from Paddle to PaddleDetection

* add unittest for detection ops

* update api & unittest

* add copyright & api name to migrate

* refactor dygraph & add mask rcnn fpn

* fix initialization & minor update

* refine architecture of mask_rcnn

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

add yolov3

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

clear directories & files for dygraph branch 

* Revert back to `fluid.clip` for gradient clipping

current API is in flux, wait for it to stabilize

* Please CI

still buggy

* #add dcn on  FCOS_head and backbone

* 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

* fcos initialization

* delete the codes not used

* pre-commit the committed code

* delete the unused function

* modify the capacity in loader from 64 to 16

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

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

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

* 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

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

* add cascade gn

* add cascade mask gn config

* update configs

* 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_ssd_config_demo

# 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.

* Clean up a bit

* Add `__shared__` annotation for shared variables between modules

* Dedup `num_classes` configurations

* Document `__shared__` usage

* Remove some unused variable

* Improve docstring and add comments for `__shared__`