* 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 PPYOLO
Co-authored-by: Nlongxiang <longxiang@baidu.com>

add htc model 

* update mbv3 ssdlite

* fix ssdlite link

* add version check

* update version check & python version for cornerpool

* 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

* 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 devices_num on reader

* refine capacity value

* refine bufsize

fix multi-scale def

* add multi-scale testing function in cascade rcnn clsaware architecture

* Replace `switch` ops with `cond`

* Use func instead of lambda

* split yolov3 loss

* add step in prior_box

* refine README

* 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.

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

* add multi-scale test

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

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

* Place mixed precision inside PaddleDetection

roll back to the monkey patch version as a temporary measure, before it is
merged into paddle

* Add command flag for `loss_scale`

* Fix a stupid indentation error

optimizer should be in the mixed precision context

* Initial FP16 training

* Add mixed precision training to rest of the detection models

* Revert "Add support for mixed precision training (#3406)"

This reverts commit 3a2c106271885071db7c0d85587540a8f83c24db.

* Bug fixes and some tweaks

* Support finetune by custom dataset

* add finetune args

* add load finetune

* reconstruct load

* add transfer learning doc

* add fruit demo

* add quick start

* add data preprocessing FAQ

* minor fix for PaddleDetection