* refine assert info in roidb_source.py

* refine image_dir assert

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

* unify reader to dataloader

* add check_version

* add CropImageWithDataAnchorSampling
* Refine bbox sampling code
* Update comments
* fix import and variable problem

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

Update ppdet/utils/checkpoint.py to skip the var shape check when the var is not initialized. (#3452)

* 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

* Initial support for distributed training

* Housekeep on rank 0 only

* Conform to models convention

* fix rcnn eval on voc

* update comment

* refine auto download logs

* Add benchmark (fps) in MODEL_ZOO doc

* minor fix for PaddleDetection

* fix bug in sharedmemory
* fix bug in sharedmemory

* add cascade gn

* add cascade mask gn config

* update configs

* fix train on VOC on multi-GPU hang

* not set persistable in parse_fetches

* fix rpn_only in cascade mask fpn

* fix rpn_only in cascade rcnn

* add gn doc

* 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