* add ttfnet enhance

* add doc

* fix pafnet training

* Add S2ANet model for Oriented Object Detection.

* add blazeface & update rcnn modelzoo

* remove condition num_priors

Merge dygraph branch into master branch.
Co-authored-by: NFDInSky <48318485+FDInSky@users.noreply.github.com>
Co-authored-by: Nsunxl1988 <47514455+sunxl1988@users.noreply.github.com>
Co-authored-by: Nwangguanzhong <jerrywgz@126.com>
Co-authored-by: Nwangxinxin08 <69842442+wangxinxin08@users.noreply.github.com>
Co-authored-by: Nwanghuancoder <wanghuancoder@163.com>
Co-authored-by: Ncnn <liuhui29@baidu.com>
Co-authored-by: NGuanghua Yu <742925032@qq.com>
Co-authored-by: NKaipeng Deng <dengkaipeng@baidu.com>
Co-authored-by: Nroot <root@bjyz-sys-gpu-kongming0.bjyz.baidu.com>

* support visualdl in preprocess data

* support most preprocess op

* add solov2 model

* fix train batch size

* add solov2_r101_vd_fpn_3x

* fix batch size and update modelzoo

* refactor code of solov2

* fix deploy/python

add htc model 

Add gridmask and random erasing methods

* Add cutmix op(#88)

* filter illegal data

* update warning message

* add yolov4

* 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

* add mask operations in RandomExpand and RandomCrop

* remove all [] in cropped polys

* is_poly -> _is_poly()

* change the judgment on whether there are polygons

* abstract is_poly to op_helper.py

* add is_mask_expand and is_mask_crop in RandomExpand and RamdomCrop

* add mask operations in RandomExpand and RandomCrop

* remove all [] in cropped polys

* is_poly -> _is_poly()

* change the judgment on whether there are polygons

* abstract is_poly to op_helper.py

* add autoaugment, which is validated on faster-rcnn

* 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.

* Optimize data transforms for yolo training

* Simplify and add docstring

* add multi-scale test

* Add face detection configs and main code.
* Integration multi-scale evaluation.

* add CropImageWithDataAnchorSampling
* Refine bbox sampling code
* Update comments
* fix import and variable problem

* Add full configs example & refine doc

* refine docs

* add_ssd_config_demo

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