* add blazeface nas demo

* fix format

* fix configs

* fix reduce_rate

* refine code & doc for cpp_infer

* add cython for pycocotools install

* load inference

* add doc

* add config file for tensorrt_infer

* add padding for rcnn preprocess

* refine code & doc

* Add GIOU loss.
* Add DIOU/CIOU loss.
* Change loss box type in bbox_head.py.
* Remove fuse_elewise_add_act_ops flag in train.py (Error may happen for elem_divbased on the flag).

- 1.add cn docs
- 2.fix fddb evaluate
- 3.fix get_shrink
- 4.delete FLAGS.dataset_dir

* split yolov3 loss

* 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 cascade_rcnn_cls_aware_r200_vd_fpn_dcnv2_nonlocal_softnms model on oidv5 and obj365.
* Add obj365 config annotation
* Update docs.

* update code & doc

to avoid cycle import when required packages are not installed

* add export_model doc

* Error out if fp16 is enabled and affine channel is used

* Add more documentation on mixed precision training

* add multi-scale test

This reverts commit b591cc133ca04dc1ed50631c8d24031bb97db18b.

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

* unify reader to dataloader

* add check_version

* refine build strategy for the model optimize test=develop

* fix according develop test=develop

* 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

* Disable optimizer fusion for RCNN models

waiting for upstream fix

* Disable completely

* Add support for mixed precision training

* Disable `fuse_all_reduce_ops` when training in mixed precision

waiting for upstream fix

* Initial support for distributed training

* Housekeep on rank 0 only

* Conform to models convention