* refine download sh to py

* update QUICK_STARTED

* Add C++ inference solution.
* Correct the link.

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

* Add more documentation on mixed precision training

* add multi-scale test

* add modes and documents for vehicle and pedestrian detection

* remove needless output images

* add class names

* add Configure for training

* fix table in READ.md

* compress the images in the demo/output

* change the score_threshold for vehicle inference

* change Yolo v3 to YOLOv3

* add class aware sampling strategy
* remove redundancy code

This reverts commit 36a2e65bb74fc8ec9d1720b3db798757b5c0d044.

This reverts commit 04bfe0a84e7ec27e5c0bdfab76aa779c45fedbe5.

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

* Document mixed precision training flags

* Clarify GPU is required for mixed precision training

* refine build strategy for the model optimize test=develop

* fix according develop test=develop

* 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)