* add devices_num on reader

* refine capacity value

* refine bufsize

fix multi-scale def

* add multi-scale testing function in cascade rcnn clsaware architecture

* Replace `switch` ops with `cond`

* Use func instead of lambda

* split yolov3 loss

* add step in prior_box

* refine README

* Polish Reader to simplify preprocessing logic.
#  sample_transforms-> make batch -> batch_transforms in Reader.
* Clean some code
* Imporve yolov3_r50vd_dcn_obj365_pretrained_coco 41.4 to 41.8.
* Update all configs.

* add softnms, nonlocal, resnet200_vd_backbone
* add CBNet
* update model zoo

* add multi-scale test

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

* Add backbone and architecture for FaceBoxes and Blazeface.
* Add dataloader for WIDERFace dataset.

* Place mixed precision inside PaddleDetection

roll back to the monkey patch version as a temporary measure, before it is
merged into paddle

* Add command flag for `loss_scale`

* Fix a stupid indentation error

optimizer should be in the mixed precision context

* Initial FP16 training

* Add mixed precision training to rest of the detection models

* Revert "Add support for mixed precision training (#3406)"

This reverts commit 3a2c106271885071db7c0d85587540a8f83c24db.

* Bug fixes and some tweaks

* 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

* minor fix for PaddleDetection

* fix rpn_only in cascade mask fpn

* fix rpn_only in cascade rcnn

* refine cascade models

* cascade-mask-fpn add

* add_ssd_config_demo

# 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 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

* Fix ResizeImage and data transform for SSD
* Fix code style

* add rpn recall function and class-aware rpn

* refine bbox_normalize in infer.py

* add is_bbox_normalize

* rename _forward to build

* check callable

* Rename object_detection to PaddleDetection
* Small fix for doc