* 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 reader in dygraph

* update dataloader some detail

* fix num_classes with background

* split config into models, optimizers, dataset, readers，runtime

* refactor dygraph & add mask rcnn fpn

* fix initialization & minor update

* refine architecture of mask_rcnn

sync reader from static ppdet

* filter illegal data

* update warning message

* add yolov4

* Make logger less noisy

* Fix indent

* fix all documentation

* fix docs conf.py

* fix some error

* fix readthedocs

* refine cocoapi import

* fix infer when anno_path is None

* 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.

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

* fix mixup error when dataset has only 1 sample

* refine log

* update code & doc

* change voc_loader

* add class aware sampling strategy
* remove redundancy code

* refine assert info in roidb_source.py

* refine image_dir assert

* Add backbone and architecture for FaceBoxes and Blazeface.
* Add dataloader for WIDERFace dataset.

* 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

* standard SENet and add a warning in coco loader

* Fix ResizeImage and data transform for SSD
* Fix code style

* Rename object_detection to PaddleDetection
* Small fix for doc