* add multi-scale test

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

* fix rcnn eval on voc

* update comment

# 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.

* fix yolov3 voc eval in train

* fix comment

* add voc_eval and yolo_darknet_voc

* add yolov3_darknet_voc in MODEL_ZOO

* fix default im_size

* fix MODEL_ZOO note

* fix is_bbox_normalized

* extract map to map_utils.py

* update yolov3_dorknet_voc mixup

* add yolov3_r34_voc

* add yolov3_mobilenet_v1_voc

* fix drop empty in VAL mode

* use cfg.num_classes

* assert metric valid

* enable difficulty can be None

* add comment for bbox_eval

* num_classes in retinanet

* Rename object_detection to PaddleDetection
* Small fix for doc

* 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.