* refactor dygraph & add mask rcnn fpn

* fix initialization & minor update

* refine architecture of mask_rcnn

add cascade rcnn and modify make net method
add new cfg method 
add auto debug tool

add yolov3

add faster rcnn\mask\cascade rcnn model arch\module\op
add base debug func in bufferdict 

clear directories & files for dygraph branch 

* add version check

* update version check & python version for cornerpool

Add `lr_multi_list` param for SSLD pretrained models' usage.

* activate scale_x_y

* update cspdarknet pretrained model

revert `reshape` changes

* optimize python path

* add yolov4

* Revert back to `fluid.clip` for gradient clipping

current API is in flux, wait for it to stabilize

* Please CI

still buggy

* #add dcn on  FCOS_head and backbone

* 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 moile-side rcnn server model

* add iou aware module
* iouaware model zoo
* fix copyright

* add mobilenet v3 configs

* fix some comment

* fix memsize

* 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

* add yolov3_mobilenet_v3

* add server side rcnn model, 62 fps with coco mAP 41.6% and 20fps with coco mAP 47.8%