* add class aware sampling strategy
* remove redundancy code

# Add VGG-SSD on VOC and COCO dataset.
# Add config and model zoo. 
# Refine bbox2out and draw_bbox:
    - Add bbox de-normalize in bbox2out function.
    - Remove bbox de-normalize in draw_bbox.

* add save best model & fix dcn configs

* fix easy problem

* add rpn recall function and class-aware rpn

* optimize error message when result is none

* Rename object_detection to PaddleDetection
* Small fix for doc

* fix x0,y0 out of bound

* clip x1/y1

* add VOC visualize

* fixn ssd_mobilenet_v1_voc.yml

* use default label

* clean TestFeed dataset config

* fix voc default label

* fix format

* fix as review

* revert voc default

* use defult label for all

* enable batch size != 1

* Unified object detection framework based on PaddlePaddle.
* Include algo: Faster, Mask, FPN, Cascade, RetinaNet, Yolo v3, SSD.