to avoid cycle import when required packages are not installed

* change voc_loader

* add x2coco.py

* Update DATA.md

* Update DATA_cn.md

* fix the labelme2coco.py

* fix the labelme2coco.py

* remove actual_shape

* add fpn fix

* refine doc for transfer learning

* add face doc
* update face detection readme and add demo jpg

* refine download sh to py

* update QUICK_STARTED

* add multi-scale test

* add class aware sampling strategy
* remove redundancy code

This reverts commit 36a2e65bb74fc8ec9d1720b3db798757b5c0d044.

This reverts commit b591cc133ca04dc1ed50631c8d24031bb97db18b.

* 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 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

* 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