* fix dygraph

* refine keep_ratio in ResizeOp

* add cascade mask

* add cascade rcnn

* update code

* remove comments

* add faster_rcnn_r50_fpn and faster_rcnn_r50

* update TestReader in dygraph

* if gt_ploy is empty, continue

* fix typo

* judge gt_ploy is empty or not

* fix judge condition

* fix gt_ploy judge

* add Mask R-CNN model

* fix mask rcnn eval

* fix mask rcnn infer

* fix mask rcnn config

* fix infer config

Co-authored-by: Nroot <root@bjyz-sys-gpu-kongming0.bjyz.baidu.com>

* 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

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