* add export_model doc, test=document_fix

* update doc

* remove fields config in input_def

* set norm_type to bn while export model

* modify code according to review

* Refine and clean code
* Fix conflicts
Co-authored-by: NKaipeng Deng <dengkaipeng@baidu.com>

* add ssd_vgg16_120e_coco

* Clean code
* rm py_op/post_processing.py and utils/data_structure.py

* fix dygraph

* refine keep_ratio in ResizeOp

* update dygraph export model

* delete get_export

* adapt faster and cascade

* 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 INSTALL_cn.md, GETTING_STARTED_cn.md, and MODEL_ZOO_cn.md for dygraph

* add Custom_DataSet.md and PrepareDataSet.md for dygraph

* add Custom_DataSet.md later

* update document

* update resnet50 pretrained weights link

* fix typo

* add set dataset path in doc, test=document_fix

* refine resume process and modify code to support eval while batch_size is larger than 1

* modify code according to review

* replace RandomDistortOp with ColorDistort

* modify RandomDistortOp

* remove hsv_format

* solve load optimizer if some key not in optimizer

* variable name tmp_key to key

* add comment

* add Mask R-CNN model

* fix mask rcnn eval

* fix mask rcnn infer

* fix mask rcnn config

* fix infer config

* fix PadBatch

* fix PadBatchOp

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

* 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 mask_rcnn_fpn model

* update smooth_l1_loss

* update smooth_l1 and sigmoid_cross_entropy_with_logits

* fix relu name

* update reader in dygraph

* update dataloader some detail

* fix num_classes with background

* rename GridMaskOp to GridMask in ppdet/data/transform/operator.py to avoid conflict

* fix bugs in operator and batch_operator and check_version

* modify name in GridMask

* add comma according to review