* add Distill model
* add distill+prune

* add fcos ttfnet coment, update modelzoo

* fix ttfnet coment

* update DataLoader & speed up Mask RCNN

* support not pad gt in rcnn model

* add comment in reader

* add ssd config file, test=kunlun

* revise file format

* support mask_rcnn for kunlun

* support faster_rcnn for kunlun

* support ppyolo for kunlun

* update ppyolo_mobilenet_v3 large & small

* Update QUICK_STARTED_cn.md (#1757)

fix typo

* cherry-pick #1757 and #1473, test=document_fix

* add ppyolo_voc

* update solov2 some detail

* fix check paddle version

* add solov2_mobilenetv3

* support infer for SOLOv2

* add ppyolo mobilenetv3

* unify log_smooth_windows and log_iter

test=develop

* remove duplicate log_iter

* remain mobile yml, since they are soft-link

test=develop

* share train_batch_size from reader to model

* update floor_divide

* add makedirs for dumping config

* 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

* expand ratio=2.0 & add ppyolo_2x_bs12.yml

* sync TrainReader.batch to global train_batch_size