* remove actual_shape

* change version to 1.5 in yolov3

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

* unify reader to dataloader

* add check_version

* 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 3a2c1062.

* 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

* add cascade gn

* add cascade mask gn config

* update configs

* fix rpn_only in cascade mask fpn

* fix rpn_only in cascade rcnn

* refine cascade models

* cascade-mask-fpn add

* add a global norm_type flag

* add group norm on fpn

* add gn on box head

* add faster rcnn fpn 50 gn config

* add mask branch norm

* update configs

* Add full configs example & refine doc

* refine docs

* 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.

* fix yolov3 voc eval in train

* fix comment

* standard SENet and add a warning in coco loader

* add deformable models
* fix dcn v2
* fix log_iter

* 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

* fix resnet for resnet34

* fix ResNet18 and ResNet34

* update modelzoo and fix configs

* fix configs

* fix resnet bn

* Clean up a bit

* Add `__shared__` annotation for shared variables between modules

* Dedup `num_classes` configurations

* Document `__shared__` usage

* Remove some unused variable

* Improve docstring and add comments for `__shared__`

* 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