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

* modify code according to review

* solve load optimizer if some key not in optimizer

* variable name tmp_key to key

* add comment

* refactor dygraph & add mask rcnn fpn

* fix initialization & minor update

* refine architecture of mask_rcnn

add train&eval 
add reader padding 
add new config 

* Make logger less noisy

* Fix indent

* add yolov3_mobilenet_v3

* refine transfer learn

* refine transfer learning doc

* Update checkpoint to use paddle 1.7 API

* Add new checkpoint support to `load_and_fusebn`

* Make yapf happy

* refine doc for transfer learning

Update ppdet/utils/checkpoint.py to skip the var shape check when the var is not initialized. (#3452)

* 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

* Initial support for distributed training

* Housekeep on rank 0 only

* Conform to models convention

Add PaddleDetection docs & some model configs

* Rename object_detection to PaddleDetection
* Small fix for doc